Arrow Research search

Author name cluster

Soheil Feizi

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

71 papers
2 author rows

Possible papers

71

NeurIPS Conference 2025 Conference Paper

A Technical Report on “Erasing the Invisible”: The 2024 NeurIPS Competition on Stress Testing Image Watermarks

  • Mucong Ding
  • Bang An
  • Tahseen Rabbani
  • Chenghao Deng
  • Anirudh Satheesh
  • Souradip Chakraborty
  • Mehrdad Saberi
  • Yuxin Wen

AI-generated images have become pervasive, raising critical concerns around content authenticity, intellectual property, and the spread of misinformation. Invisible watermarks offer a promising solution for identifying AI-generated images, preserving content provenance without degrading visual quality. However, their real-world robustness remains uncertain due to the lack of standardized evaluation protocols and large-scale stress testing. To bridge this gap, we organized “Erasing the Invisible, ” a NeurIPS 2024 competition and newly established benchmark designed to systematically stress testing the resilience of watermarking techniques. The competition introduced two attack tracks—Black-box and Beige-box—that simulate practical scenarios with varying levels of attacker knowledge on watermarks, providing a comprehensive assessment of watermark robustness. The competition attracted significant global participation, with 2, 722 submissions from 298 teams. Through a rigorous evaluation pipeline featuring real-time feedback and human-verified final rankings, participants developed and demonstrated new attack strategies that revealed critical vulnerabilities in state-of-the-art watermarking methods. On average, the top-5 teams in both tracks could remove watermarks from $\geq$ 89% of the images while preserving high visual quality, setting strong baselines for future research on watermark attacks and defenses. To support continued progress in this field, we summarize the insights and lessons learned from this competition in this paper, and release the benchmark dataset, evaluation toolkit, and competition results. “Erasing the Invisible” establishes a valuable open resource for advancing more robust watermarking techniques and strengthening content provenance in the era of generative AI.

PDF Details

NeurIPS Conference 2025 Conference Paper

Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text

  • Yize Cheng
  • Vinu Sankar Sadasivan
  • Mehrdad Saberi
  • Shoumik Saha
  • Soheil Feizi

The increasing capabilities of Large Language Models (LLMs) have raised concerns about their misuse in AI-generated plagiarism and social engineering. While various AI-generated text detectors have been proposed to mitigate these risks, many remain vulnerable to simple evasion techniques such as paraphrasing. However, recent detectors have shown greater robustness against such basic attacks. In this work, we introduce \textbf{Adversarial Paraphrasing}, a training-free attack framework that universally humanizes any AI-generated text to evade detection more effectively. Our approach leverages an off-the-shelf instruction-following LLM to paraphrase AI-generated content under the guidance of an AI text detector, producing adversarial examples that are specifically optimized to bypass detection. Extensive experiments show that our attack is both broadly effective and highly transferable across several detection systems. For instance, compared to simple paraphrasing attack—which, ironically, increases the true positive at 1\% false positive (T@1\%F) by 8. 57\% on RADAR and 15. 03\% on Fast-DetectGPT—adversarial paraphrasing, guided by OpenAI-RoBERTa-Large, reduces T@1\%F by 64. 49\% on RADAR and a striking 98. 96\% on Fast-DetectGPT. Across a diverse set of detectors—including neural network-based, watermark-based, and zero-shot approaches—our attack achieves an average T@1\%F reduction of 87. 88\% under the guidance of OpenAI-RoBERTa-Large. We also analyze the tradeoff between text quality and our attack success to find that our method can significantly reduce detection rates, with mostly a slight degradation in text quality. Our novel adversarial setup highlights the need for more robust and resilient detection strategies in the light of increasingly sophisticated evasion techniques.

PDF Details

TMLR Journal 2025 Journal Article

Can AI-Generated Text be Reliably Detected? Stress Testing AI Text Detectors Under Various Attacks

  • Vinu Sankar Sadasivan
  • Aounon Kumar
  • Sriram Balasubramanian
  • Wenxiao Wang
  • Soheil Feizi

Large Language Models (LLMs) can perform impressively well in various applications, such as document completion and question-answering. However, the potential for misuse of these models in activities such as plagiarism, generating fake news, and spamming has raised concerns about their responsible use. Consequently, the reliable detection of AI-generated text has become a critical area of research. Recent works have attempted to address this challenge through various methods, including the identification of model signatures in generated text outputs and the application of watermarking techniques to detect AI-generated text. These detectors have shown to be effective under their specific settings. In this paper, we stress-test the robustness of these AI text detectors in the presence of an attacker. We introduce recursive paraphrasing attack to stress test a wide range of detection schemes, including the ones using the watermarking as well as neural network-based detectors, zero-shot classifiers, and retrieval-based detectors. Our experiments conducted on passages, each approximately 300 tokens long, reveal the varying sensitivities of these detectors to our attacks. We also observe that these paraphrasing attacks add slight degradation to the text quality. We analyze the trade-offs between our attack strength and the resulting text quality, measured through human studies, perplexity scores, and accuracy on text benchmarks. Our findings indicate that while our recursive paraphrasing method can significantly reduce detection rates, it only slightly degrades text quality in many cases, highlighting potential vulnerabilities in current detection systems in the presence of an attacker. Additionally, we investigate the susceptibility of watermarked LLMs to spoofing attacks aimed at misclassifying human-written text as AI-generated. We demonstrate that an attacker can infer hidden AI text signatures without white-box access to the detection method, potentially leading to reputational risks for LLM developers. Finally, we provide a theoretical framework connecting the AUROC of the best possible detector to the Total Variation distance between human and AI text distributions. This analysis offers insights into the fundamental challenges of reliable detection as language models continue to advance.

PDF Details

ICLR Conference 2025 Conference Paper

How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodings

  • Samuel Audia
  • Soheil Feizi
  • Matthias Zwicker
  • Dinesh Manocha

Neural networks that map between low dimensional spaces are ubiquitous in computer graphics and scientific computing; however, in their naive implementation, they are unable to learn high frequency information. We present a comprehensive analysis comparing the two most common techniques for mitigating this spectral bias: Fourier feature encodings (FFE) and multigrid parametric encodings (MPE). FFEs are seen as the standard for low dimensional mappings, but MPEs often outperform them and learn representations with higher resolution and finer detail. FFE's roots in the Fourier transform, make it susceptible to aliasing if pushed too far, while MPEs, which use a learned grid structure, have no such limitation. To understand the difference in performance, we use the neural tangent kernel (NTK) to evaluate these encodings through the lens of an analogous kernel regression. By finding a lower bound on the smallest eigenvalue of the NTK, we prove that MPEs improve a network's performance through the structure of their grid and not their learnable embedding. This mechanism is fundamentally different from FFEs, which rely solely on their embedding space to improve performance. Results are empirically validated on a 2D image regression task using images taken from 100 synonym sets of ImageNet and 3D implicit surface regression on objects from the Stanford graphics dataset. Using peak signal-to-noise ratio (PSNR) and multiscale structural similarity (MS-SSIM) to evaluate how well fine details are learned, we show that the MPE increases the minimum eigenvalue by 8 orders of magnitude over the baseline and 2 orders of magnitude over the FFE. The increase in spectrum corresponds to a 15 dB (PSNR) / 0.65 (MS-SSIM) increase over baseline and a 12 dB (PSNR) / 0.33 (MS-SSIM) increase over the FFE.

Details

NeurIPS Conference 2025 Conference Paper

Localizing Knowledge in Diffusion Transformers

  • Arman Zarei
  • Samyadeep Basu
  • Keivan Rezaei
  • Zihao Lin
  • Sayan Nag
  • Soheil Feizi

Understanding how knowledge is distributed across the layers of generative models is crucial for improving interpretability, controllability, and adaptation. While prior work has explored knowledge localization in UNet-based architectures, Diffusion Transformer (DiT)-based models remain underexplored in this context. In this paper, we propose a model- and knowledge-agnostic method to localize where specific types of knowledge are encoded within the DiT blocks. We evaluate our method on state-of-the-art DiT-based models, including PixArt-$\alpha$, FLUX, and SANA, across six diverse knowledge categories. We show that the identified blocks are both interpretable and causally linked to the expression of knowledge in generated outputs. Building on these insights, we apply our localization framework to two key applications: *model personalization* and *knowledge unlearning*. In both settings, our localized fine-tuning approach enables efficient and targeted updates, reducing computational cost, improving task-specific performance, and better preserving general model behavior with minimal interference to unrelated or surrounding content. Overall, our findings offer new insights into the internal structure of DiTs and introduce a practical pathway for more interpretable, efficient, and controllable model editing.

PDF Details

TMLR Journal 2025 Journal Article

RESTOR: Knowledge Recovery in Machine Unlearning

  • Keivan Rezaei
  • Khyathi Chandu
  • Soheil Feizi
  • Yejin Choi
  • Faeze Brahman
  • Abhilasha Ravichander

Large language models trained on web-scale corpora can memorize undesirable data containing misinformation, copyrighted material, or private or sensitive information. Recently, several machine unlearning algorithms have been proposed to eliminate the effect of such datapoints from trained models-- that is, to approximate *a model that had never been trained on these datapoints in the first place*. However, evaluating the effectiveness of unlearning algorithms remains an open challenge. Previous work has relied on heuristics-- such as verifying that the model can no longer reproduce the specific information targeted for removal while maintaining accuracy on unrelated test data. These approaches inadequately capture the complete effect of reversing the influence of datapoints on a trained model. In this work, we propose the RESTOR framework for machine unlearning evaluation, which assesses the ability of unlearning algorithms for targeted data erasure, by evaluating the ability of models to forget the knowledge introduced in these datapoints, while simultaneously recovering the model's knowledge state had it never encountered these datapoints. RESTOR helps uncover several novel insights about popular unlearning algorithms, and the mechanisms through which they operate-- for instance, identifying that some algorithms merely emphasize forgetting but not recovering knowledge, and that localizing unlearning targets can enhance unlearning performance.

PDF Details

ICLR Conference 2025 Conference Paper

Rethinking Artistic Copyright Infringements In the Era Of Text-to-Image Generative Models

  • Mazda Moayeri
  • Sriram Balasubramanian
  • Samyadeep Basu
  • Priyatham Kattakinda
  • Atoosa Malemir Chegini
  • Robert Brauneis
  • Soheil Feizi

The advent of text-to-image generative models has led artists to worry that their individual styles may be copied, creating a pressing need to reconsider the lack of protection for artistic styles under copyright law. This requires answering challenging questions, like what defines style and what constitutes style infringment. In this work, we build on prior legal scholarship to develop an automatic and interpretable framework to \emph{quantitatively} assess style infringement. Our methods hinge on a simple logical argument: if an artist's works can consistently be recognized as their own, then they have a unique style. Based on this argument, we introduce ArtSavant, a practical (i.e., efficient and easy to understand) tool to (i) determine the unique style of an artist by comparing it to a reference corpus of works from hundreds of artists, and (ii) recognize if the identified style reappears in generated images. We then apply ArtSavant in an empirical study to quantify the prevalence of artistic style copying across 3 popular text-to-image generative models, finding that under simple prompting, $20\\%$ of $372$ prolific artists studied appear to have their styles be at risk of copying by today's generative models. Our findings show that prior legal arguments can be operationalized in quantitative ways, towards more nuanced examination of the issue of artistic style infringements.

Details

ICLR Conference 2025 Conference Paper

Unearthing Skill-level Insights for Understanding Trade-offs of Foundation Models

  • Mazda Moayeri
  • Vidhisha Balachandran
  • Varun Chandrasekaran
  • Safoora Yousefi
  • Thomas Fel
  • Soheil Feizi
  • Besmira Nushi
  • Neel Joshi

With models getting stronger, evaluations have grown more complex, testing multiple skills in one benchmark and even in the same instance at once. However, skill-wise performance is obscured when inspecting aggregate accuracy, under-utilizing the rich signal modern benchmarks contain. We propose an automatic approach to recover the underlying skills relevant for any evaluation instance, by way of inspecting model-generated {\em rationales}. After validating the relevance of rationale-parsed skills and inferring skills for $46$k instances over $12$ benchmarks, we observe many skills to be common across benchmarks, resulting in the curation of hundreds of \emph{skill-slices} (i.e. sets of instances testing a common skill). Inspecting accuracy over these slices yields novel insights on model trade-offs: e.g., compared to GPT-4o and Claude 3.5 Sonnet, on average, Gemini 1.5 Pro is $18\%$ more accurate in \emph{computing molar mass}, but $19\\%$ less accurate in \emph{applying constitutional law}, despite the overall accuracies of the three models differing by a mere $0.4\\%$. Furthermore, we demonstrate the practical utility of our approach by showing that insights derived from skill slice analysis can generalize to held-out instances: when routing each instance to the model strongest on the relevant skills, we see a $3\\%$ accuracy improvement over our $12$ dataset corpus. Our skill-slices and framework open a new avenue in model evaluation, leveraging skill-specific analyses to unlock a more granular and actionable understanding of model capabilities.

Details

NeurIPS Conference 2024 Conference Paper

Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP

  • Sriram Balasubramanian
  • Samyadeep Basu
  • Soheil Feizi

Recent work has explored how individual components of the CLIP-ViT model contribute to the final representation by leveraging the shared image-text representation space of CLIP. These components, such as attention heads and MLPs, have been shown to capture distinct image features like shape, color or texture. However, understanding the role of these components in arbitrary vision transformers (ViTs) is challenging. To this end, we introduce a general framework which can identify the roles of various components in ViTs beyond CLIP. Specifically, we (a) automate the decomposition of the final representation into contributions from different model components, and (b) linearly map these contributions to CLIP space to interpret them via text. Additionally, we introduce a novel scoring function to rank components by their importance with respect to specific features. Applying our framework to various ViT variants (e. g. DeiT, DINO, DINOv2, Swin, MaxViT), we gain insights into the roles of different components concerning particular image features. These insights facilitate applications such as image retrieval using text descriptions or reference images, visualizing token importance heatmaps, and mitigating spurious correlations. We release our code to reproduce the experiments in the paper.

PDF Details DOI

ICLR Conference 2024 Conference Paper

DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness

  • Shoumik Saha
  • Wenxiao Wang 0002
  • Yigitcan Kaya
  • Soheil Feizi
  • Tudor Dumitras

Machine Learning (ML) models have been utilized for malware detection for over two decades. Consequently, this ignited an ongoing arms race between malware authors and antivirus systems, compelling researchers to propose defenses for malware-detection models against evasion attacks. However, most if not all existing defenses against evasion attacks suffer from sizable performance degradation and/or can defend against only specific attacks, which makes them less practical in real-world settings. In this work, we develop a certified defense, DRSM (De-Randomized Smoothed MalConv), by redesigning the *de-randomized smoothing* technique for the domain of malware detection. Specifically, we propose a *window ablation* scheme to provably limit the impact of adversarial bytes while maximally preserving local structures of the executables. After showing how DRSM is theoretically robust against attacks with contiguous adversarial bytes, we verify its performance and certified robustness experimentally, where we observe only marginal accuracy drops as the cost of robustness. To our knowledge, we are the first to offer certified robustness in the realm of static detection of malware executables. More surprisingly, through evaluating DRSM against $9$ empirical attacks of different types, we observe that the proposed defense is empirically robust to some extent against a diverse set of attacks, some of which even fall out of the scope of its original threat model. In addition, we collected $15.5K$ recent benign raw executables from diverse sources, which will be made public as a dataset called PACE (Publicly Accessible Collection(s) of Executables) to alleviate the scarcity of publicly available benign datasets for studying malware detection and provide future research with more representative data of the time. Our code and dataset are available at - https://github.com/ShoumikSaha/DRSM

Details

ICML Conference 2024 Conference Paper

Fast Adversarial Attacks on Language Models In One GPU Minute

  • Vinu Sankar Sadasivan
  • Shoumik Saha
  • Gaurang Sriramanan
  • Priyatham Kattakinda
  • Atoosa Malemir Chegini
  • Soheil Feizi

In this paper, we introduce a novel class of fast, beam search-based adversarial attack (BEAST) for Language Models (LMs). BEAST employs interpretable parameters, enabling attackers to balance between attack speed, success rate, and the readability of adversarial prompts. The computational efficiency of BEAST facilitates us to investigate its applications on LMs for jailbreaking, eliciting hallucinations, and privacy attacks. Our gradient-free targeted attack can jailbreak aligned LMs with high attack success rates within one minute. For instance, BEAST can jailbreak Vicuna-7B-v1. 5 under one minute with a success rate of 89% when compared to a gradient-based baseline that takes over an hour to achieve 70% success rate using a single Nvidia RTX A6000 48GB GPU. BEAST can also generate adversarial suffixes for successful jailbreaks that can transfer to unseen prompts and unseen models such as GPT-4-Turbo. Additionally, we discover a unique outcome wherein our untargeted attack induces hallucinations in LM chatbots. Through human evaluations, we find that our untargeted attack causes Vicuna-7B-v1. 5 to produce $\sim$15% more incorrect outputs when compared to LM outputs in the absence of our attack. We also learn that 22% of the time, BEAST causes Vicuna to generate outputs that are not relevant to the original prompt. Further, we use BEAST to generate adversarial prompts in a few seconds that can boost the performance of existing membership inference attacks for LMs. We believe that our fast attack, BEAST, has the potential to accelerate research in LM security and privacy.

Details

NeurIPS Conference 2024 Conference Paper

LLM-Check: Investigating Detection of Hallucinations in Large Language Models

  • Gaurang Sriramanan
  • Siddhant Bharti
  • Vinu Sankar Sadasivan
  • Shoumik Saha
  • Priyatham Kattakinda
  • Soheil Feizi

While Large Language Models (LLMs) have become immensely popular due to their outstanding performance on a broad range of tasks, these models are prone to producing hallucinations— outputs that are fallacious or fabricated yet often appear plausible or tenable at a glance. In this paper, we conduct a comprehensive investigation into the nature of hallucinations within LLMs and furthermore explore effective techniques for detecting such inaccuracies in various real-world settings. Prior approaches to detect hallucinations in LLM outputs, such as consistency checks or retrieval-based methods, typically assume access to multiple model responses or large databases. These techniques, however, tend to be computationally expensive in practice, thereby limiting their applicability to real-time analysis. In contrast, in this work, we seek to identify hallucinations within a single response in both white-box and black-box settings by analyzing the internal hidden states, attention maps, and output prediction probabilities of an auxiliary LLM. In addition, we also study hallucination detection in scenarios where ground-truth references are also available, such as in the setting of Retrieval-Augmented Generation (RAG). We demonstrate that the proposed detection methods are extremely compute-efficient, with speedups of up to 45x and 450x over other baselines, while achieving significant improvements in detection performance over diverse datasets.

PDF Details DOI

ICLR Conference 2024 Conference Paper

Localizing and Editing Knowledge In Text-to-Image Generative Models

  • Samyadeep Basu
  • Nanxuan Zhao
  • Vlad I. Morariu
  • Soheil Feizi
  • Varun Manjunatha

Text-to-Image Diffusion Models such as Stable-Diffusion and Imagen have achieved unprecedented quality of photorealism with state-of-the-art FID scores on MS-COCO and other generation benchmarks. Given a caption, image generation requires fine-grained knowledge about attributes such as object structure, style, and viewpoint amongst others. Where does this information reside in text-to-image generative models? In our paper, we tackle this question and understand how knowledge corresponding to distinct visual attributes is stored in large-scale text-to-image diffusion models. We adapt Causal Mediation Analysis for text-to-image models and trace knowledge about distinct visual attributes to various (causal) components in the (i) UNet and (ii) text-encoder of the diffusion model. In particular, we show that unlike large-language models, knowledge about different attributes is not localized in isolated components, but is instead distributed amongst a set of components in the conditional UNet. These sets of components are often distinct for different visual attributes (e.g., style} / objects). Remarkably, we find that the text-encoder in public text-to-image models such as Stable-Diffusion contains {\it only} one causal state across different visual attributes, and this is the first self-attention layer corresponding to the last subject token of the attribute in the caption. This is in stark contrast to the causal states in other language models which are often the mid-MLP layers. Based on this observation of only one causal state in the text-encoder, we introduce a fast, data-free model editing method DiffQuickFix which can effectively edit concepts (remove or update knowledge) in text-to-image models. DiffQuickFix can edit (ablate) concepts in under a second with a closed-form update, providing a significant 1000x speedup and comparable editing performance to existing fine-tuning based editing methods.

Details

NeurIPS Conference 2024 Conference Paper

Loki: Low-rank Keys for Efficient Sparse Attention

  • Prajwal Singhania
  • Siddharth Singh
  • Shwai He
  • Soheil Feizi
  • Abhinav Bhatele

Inference on large language models (LLMs) can be expensive in terms of thecompute and memory costs involved, especially when long sequence lengths areused. In particular, the self-attention mechanism used in LLM inference contributessignificantly to these costs, which has sparked an interest in approximating the self-attention computation to reduce such costs. In this work, we propose to approximateself-attention by focusing on the dimensionality of key vectors computed in theattention block. Our analysis reveals that key vectors lie in a significantly lower-dimensional space, consistently across several datasets and models. Exploiting thisobservation, we propose Loki, a novel sparse attention method that ranks and selectstokens in the KV-cache based on attention scores computed in low-dimensionalspace. Our evaluations show that Loki is able to speed up the attention computationdue to reduced data movement (load/store) and compute costs while maintainingthe efficacy of the models better than other popular approximation methods.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Measuring Self-Supervised Representation Quality for Downstream Classification Using Discriminative Features

  • Neha Kalibhat
  • Kanika Narang
  • Hamed Firooz
  • Maziar Sanjabi
  • Soheil Feizi

Self-supervised learning (SSL) has shown impressive results in downstream classification tasks. However, there is limited work in understanding their failure modes and interpreting their learned representations. In this paper, we study the representation space of state-of-the-art self-supervised models including SimCLR, SwaV, MoCo, BYOL, DINO, SimSiam, VICReg and Barlow Twins. Without the use of class label information, we discover discriminative features that correspond to unique physical attributes in images, present mostly in correctly-classified representations. Using these features, we can compress the representation space by up to$40% without significantly affecting linear classification performance. We then propose Self-Supervised Representation Quality Score (or Q-Score), an unsupervised score that can reliably predict if a given sample is likely to be mis-classified during linear evaluation, achieving AUPRC of 91.45 on ImageNet-100 and 78.78 on ImageNet-1K. Q-Score can also be used as a regularization term on pre-trained encoders to remedy low-quality representations. Fine-tuning with Q-Score regularization can boost the linear probing accuracy of SSL models by up to 5.8% on ImageNet-100 and 3.7% on ImageNet-1K compared to their baselines. Finally, using gradient heatmaps and Salient ImageNet masks, we define a metric to quantify the interpretability of each representation. We show that discriminative features are strongly correlated to core attributes and, enhancing these features through Q-score regularization makes SSL representations more interpretable.

PDF Details DOI

ICML Conference 2024 Conference Paper

On Mechanistic Knowledge Localization in Text-to-Image Generative Models

  • Samyadeep Basu
  • Keivan Rezaei
  • Priyatham Kattakinda
  • Vlad I. Morariu
  • Nanxuan Zhao
  • Ryan A. Rossi
  • Varun Manjunatha
  • Soheil Feizi

Identifying layers within text-to-image models which control visual attributes can facilitate efficient model editing through closed-form updates. Recent work, leveraging causal tracing show that early Stable-Diffusion variants confine knowledge primarily to the first layer of the CLIP text-encoder, while it diffuses throughout the UNet. Extending this framework, we observe that for recent models (e. g. , SD-XL, DeepFloyd), causal tracing fails in pinpointing localized knowledge, highlighting challenges in model editing. To address this issue, we introduce the concept of mechanistic localization in text-to-image models, where knowledge about various visual attributes (e. g. , "style", "objects", "facts") can be mechanistically localized to a small fraction of layers in the UNet, thus facilitating efficient model editing. We localize knowledge using our method LocoGen which measures the direct effect of intermediate layers to output generation by performing interventions in the cross-attention layers of the UNet. We then employ LocoEdit, a fast closed-form editing method across popular open-source text-to-image models (including the latest SD-XL) and explore the possibilities of neuron-level model editing. Using mechanistic localization, our work offers a better view of successes and failures in localization-based text-to-image model editing.

Details

ICLR Conference 2024 Conference Paper

PRIME: Prioritizing Interpretability in Failure Mode Extraction

  • Keivan Rezaei
  • Mehrdad Saberi
  • Mazda Moayeri
  • Soheil Feizi

In this work, we study the challenge of providing human-understandable descriptions for failure modes in trained image classification models. Existing works address this problem by first identifying clusters (or directions) of incorrectly classified samples in a latent space and then aiming to provide human-understandable text descriptions for them. We observe that in some cases, describing text does not match well with identified failure modes, partially owing to the fact that shared interpretable attributes of failure modes may not be captured using clustering in the feature space. To improve on these shortcomings, we propose a novel approach that prioritizes interpretability in this problem: we start by obtaining human-understandable concepts (tags) of images in the dataset and then analyze the model's behavior based on the presence or absence of combinations of these tags. Our method also ensures that the tags describing a failure mode form a minimal set, avoiding redundant and noisy descriptions. Through several experiments on different datasets, we show that our method successfully identifies failure modes and generates high-quality text descriptions associated with them. These results highlight the importance of prioritizing interpretability in understanding model failures.

Details

ICLR Conference 2024 Conference Paper

Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks

  • Mehrdad Saberi
  • Vinu Sankar Sadasivan
  • Keivan Rezaei
  • Aounon Kumar
  • Atoosa Malemir Chegini
  • Wenxiao Wang 0002
  • Soheil Feizi

In light of recent advancements in generative AI models, it has become essential to distinguish genuine content from AI-generated one to prevent the malicious usage of fake materials as authentic ones and vice versa. Various techniques have been introduced for identifying AI-generated images, with watermarking emerging as a promising approach. In this paper, we analyze the robustness of various AI-image detectors including watermarking and classifier-based deepfake detectors. For watermarking methods that introduce subtle image perturbations (i.e., low perturbation budget methods), we reveal a fundamental trade-off between the evasion error rate (i.e., the fraction of watermarked images detected as non-watermarked ones) and the spoofing error rate (i.e., the fraction of non-watermarked images detected as watermarked ones) upon an application of a diffusion purification attack. In this regime, we also empirically show that diffusion purification effectively removes watermarks with minimal changes to images. For high perturbation watermarking methods where notable changes are applied to images, the diffusion purification attack is not effective. In this case, we develop a model substitution adversarial attack that can successfully remove watermarks. Moreover, we show that watermarking methods are vulnerable to spoofing attacks where the attacker aims to have real images (potentially obscene) identified as watermarked ones, damaging the reputation of the developers. In particular, by just having black-box access to the watermarking method, we show that one can generate a watermarked noise image which can be added to the real images to have them falsely flagged as watermarked ones. Finally, we extend our theory to characterize a fundamental trade-off between the robustness and reliability of classifier-based deep fake detectors and demonstrate it through experiments. Code is available at https://github.com/mehrdadsaberi/watermark_robustness.

Details

AAAI Conference 2024 Conference Paper

Strong Baselines for Parameter-Efficient Few-Shot Fine-Tuning

  • Samyadeep Basu
  • Shell Hu
  • Daniela Massiceti
  • Soheil Feizi

Few-shot classification (FSC) entails learning novel classes given only a few examples per class after a pre-training (or meta-training) phase on a set of base classes. Recent works have shown that simply fine-tuning a pre-trained Vision Transformer (ViT) on new test classes is a strong approach for FSC. Fine-tuning ViTs, however, is expensive in time, compute and storage. This has motivated the design of parameter efficient fine-tuning (PEFT) methods which fine-tune only a fraction of the Transformer's parameters. While these methods have shown promise, inconsistencies in experimental conditions make it difficult to disentangle their advantage from other experimental factors including the feature extractor architecture, pre-trained initialization and fine-tuning algorithm, amongst others. In our paper, we conduct a large-scale, experimentally consistent, empirical analysis to study PEFTs for few-shot image classification. Through a battery of over 1.8k controlled experiments on large-scale few-shot benchmarks including Meta-Dataset and ORBIT, we uncover novel insights on PEFTs that cast light on their efficacy in fine-tuning ViTs for few-shot classification. Through our controlled empirical study, we have two main findings: (i) Fine-tuning just the LayerNorm parameters (which we call LN-Tune) during few-shot adaptation is an extremely strong baseline across ViTs pre-trained with both self-supervised and supervised objectives, (ii) For self-supervised ViTs, we find that simply learning a set of scaling parameters for each attention matrix (which we call Attn-Scale) along with a domain-residual adapter (DRA) module leads to state-of-the-art performance (while being ~9x more parameter-efficient) on Meta-Dataset. Our empirical findings set strong baselines and call for rethinking the current design of PEFT methods for FSC.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Understanding Information Storage and Transfer in Multi-Modal Large Language Models

  • Samyadeep Basu
  • Martin Grayson
  • Cecily Morrison
  • Besmira Nushi
  • Soheil Feizi
  • Daniela Massiceti

Understanding the mechanisms of information storage and transfer in Transformer-based models is important for driving model understanding progress. Recent work has studied these mechanisms for Large Language Models (LLMs), revealing insights on how information is stored in a model's parameters and how information flows to and from these parameters in response to specific prompts. However, these studies have not yet been extended to Multi-modal Large Language Models (MLLMs). Given their expanding capabilities and real-world use, we start by studying one aspect of these models -- how MLLMs process information in a factual visual question answering task. We use a constraint-based formulation which views a visual question as having a set of visual or textual constraints that the model's generated answer must satisfy to be correct (e. g. What movie directed by \emph{the director in this photo} has won a \emph{Golden Globe}? ). Under this setting, we contribute i) a method that extends causal information tracing from pure language to the multi-modal setting, and ii) \emph{VQA-Constraints}, a test-bed of 9. 7K visual questions annotated with constraints. We use these tools to study two open-source MLLMs, LLaVa and multi-modal Phi-2. Our key findings show that these MLLMs rely on MLP and self-attention blocks in much earlier layers for information storage, compared to LLMs whose mid-layer MLPs are more important. We also show that a consistent small subset of visual tokens output by the vision encoder are responsible for transferring information from the image to these causal blocks. We validate these mechanisms by introducing MultEdit a model-editing algorithm that can correct errors and insert new long-tailed information into MLLMs by targeting these causal blocks. We will publicly release our dataset and code.

PDF Details DOI

ICLR Conference 2023 Conference Paper

Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication

  • Yanchao Sun
  • Ruijie Zheng
  • Parisa Hassanzadeh
  • Yongyuan Liang
  • Soheil Feizi
  • Sumitra Ganesh
  • Furong Huang

Communication is important in many multi-agent reinforcement learning (MARL) problems for agents to share information and make good decisions. However, when deploying trained communicative agents in a real-world application where noise and potential attackers exist, the safety of communication-based policies becomes a severe issue that is underexplored. Specifically, if communication messages are manipulated by malicious attackers, agents relying on untrustworthy communication may take unsafe actions that lead to catastrophic consequences. Therefore, it is crucial to ensure that agents will not be misled by corrupted communication, while still benefiting from benign communication. In this work, we consider an environment with $N$ agents, where the attacker may arbitrarily change the communication from any $C<\frac{N-1}{2}$ agents to a victim agent. For this strong threat model, we propose a certifiable defense by constructing a message-ensemble policy that aggregates multiple randomly ablated message sets. Theoretical analysis shows that this message-ensemble policy can utilize benign communication while being certifiably robust to adversarial communication, regardless of the attacking algorithm. Experiments in multiple environments verify that our defense significantly improves the robustness of trained policies against various types of attacks.

Details

NeurIPS Conference 2023 Conference Paper

Diffused Redundancy in Pre-trained Representations

  • Vedant Nanda
  • Till Speicher
  • John Dickerson
  • Krishna Gummadi
  • Soheil Feizi
  • Adrian Weller

Representations learned by pre-training a neural network on a large dataset are increasingly used successfully to perform a variety of downstream tasks. In this work, we take a closer look at how features are encoded in such pre-trained representations. We find that learned representations in a given layer exhibit a degree of diffuse redundancy, ie, any randomly chosen subset of neurons in the layer that is larger than a threshold size shares a large degree of similarity with the full layer and is able to perform similarly as the whole layer on a variety of downstream tasks. For example, a linear probe trained on $20\%$ of randomly picked neurons from the penultimate layer of a ResNet50 pre-trained on ImageNet1k achieves an accuracy within $5\%$ of a linear probe trained on the full layer of neurons for downstream CIFAR10 classification. We conduct experiments on different neural architectures (including CNNs and Transformers) pre-trained on both ImageNet1k and ImageNet21k and evaluate a variety of downstream tasks taken from the VTAB benchmark. We find that the loss \& dataset used during pre-training largely govern the degree of diffuse redundancy and the "critical mass" of neurons needed often depends on the downstream task, suggesting that there is a task-inherent redundancy-performance Pareto frontier. Our findings shed light on the nature of representations learned by pre-trained deep neural networks and suggest that entire layers might not be necessary to perform many downstream tasks. We investigate the potential for exploiting this redundancy to achieve efficient generalization for downstream tasks and also draw caution to certain possible unintended consequences. Our code is available at \url{https: //github. com/nvedant07/diffused-redundancy}.

PDF Details

NeurIPS Conference 2023 Conference Paper

Exploring Geometry of Blind Spots in Vision models

  • Sriram Balasubramanian
  • Gaurang Sriramanan
  • Vinu Sankar Sadasivan
  • Soheil Feizi

Despite the remarkable success of deep neural networks in a myriad of settings, several works have demonstrated their overwhelming sensitivity to near-imperceptible perturbations, known as adversarial attacks. On the other hand, prior works have also observed that deep networks can be under-sensitive, wherein large-magnitude perturbations in input space do not induce appreciable changes to network activations. In this work, we study in detail the phenomenon of under-sensitivity in vision models such as CNNs and Transformers, and present techniques to study the geometry and extent of “equi-confidence” level sets of such networks. We propose a Level Set Traversal algorithm that iteratively explores regions of high confidence with respect to the input space using orthogonal components of the local gradients. Given a source image, we use this algorithm to identify inputs that lie in the same equi-confidence level set as the source image despite being perceptually similar to arbitrary images from other classes. We further observe that the source image is linearly connected by a high-confidence path to these inputs, uncovering a star-like structure for level sets of deep networks. Furthermore, we attempt to identify and estimate the extent of these connected higher-dimensional regions over which the model maintains a high degree of confidence.

PDF Details

AAAI Conference 2023 Conference Paper

Goal-Conditioned Q-learning as Knowledge Distillation

  • Alexander Levine
  • Soheil Feizi

Many applications of reinforcement learning can be formalized as goal-conditioned environments, where, in each episode, there is a "goal" that affects the rewards obtained during that episode but does not affect the dynamics. Various techniques have been proposed to improve performance in goal-conditioned environments, such as automatic curriculum generation and goal relabeling. In this work, we explore a connection between off-policy reinforcement learning in goal-conditioned settings and knowledge distillation. In particular: the current Q-value function and the target Q-value estimate are both functions of the goal, and we would like to train the Q-value function to match its target for all goals. We therefore apply Gradient-Based Attention Transfer (Zagoruyko and Komodakis 2017), a knowledge distillation technique, to the Q-function update. We empirically show that this can improve the performance of goal-conditioned off-policy reinforcement learning when the space of goals is high-dimensional. We also show that this technique can be adapted to allow for efficient learning in the case of multiple simultaneous sparse goals, where the agent can attain a reward by achieving any one of a large set of objectives, all specified at test time. Finally, to provide theoretical support, we give examples of classes of environments where (under some assumptions) standard off-policy algorithms such as DDPG require at least O(d^2) replay buffer transitions to learn an optimal policy, while our proposed technique requires only O(d) transitions, where d is the dimensionality of the goal and state space. Code and appendix are available at https://github.com/alevine0/ReenGAGE.

PDF Details DOI

ICLR Conference 2023 Conference Paper

Hard-Meta-Dataset++: Towards Understanding Few-Shot Performance on Difficult Tasks

  • Samyadeep Basu
  • Megan Stanley
  • John Bronskill
  • Soheil Feizi
  • Daniela Massiceti

Few-shot classification is the ability to adapt to any new classification task from only a few training examples. The performance of current top-performing few-shot classifiers varies widely across different tasks where they often fail on a subset of `difficult' tasks. This phenomenon has real-world consequences for deployed few-shot systems where safety and reliability are paramount, yet little has been done to understand these failure cases. In this paper, we study these difficult tasks to gain a more nuanced understanding of the limitations of current methods. To this end, we develop a general and computationally efficient algorithm called FastDiffSel to extract difficult tasks from any large-scale vision dataset. Notably, our algorithm can extract tasks at least 20x faster than existing methods enabling its use on large-scale datasets. We use FastDiffSel to extract difficult tasks from Meta-Datasset, a widely-used few-shot classification benchmark, and other challenging large-scale vision datasets including ORBIT, CURE-OR and ObjectNet. These tasks are curated into Hard-MD++, a new few-shot testing benchmark to promote the development of methods that are robust to even the most difficult tasks. We use Hard-MD++ to stress-test an extensive suite of few-shot classification methods and show that state-of-the-art approaches fail catastrophically on difficult tasks. We believe that our extraction algorithm FastDiffSel and Hard-MD++ will aid researchers in further understanding failure modes of few-shot classification models.

Details

ICML Conference 2023 Conference Paper

Identifying Interpretable Subspaces in Image Representations

  • Neha Mukund Kalibhat
  • Shweta Bhardwaj
  • C. Bayan Bruss
  • Hamed Firooz
  • Maziar Sanjabi
  • Soheil Feizi

We propose Automatic Feature Explanation using Contrasting Concepts (FALCON), an interpretability framework to explain features of image representations. For a target feature, FALCON captions its highly activating cropped images using a large captioning dataset (like LAION-400m) and a pre-trained vision-language model like CLIP. Each word among the captions is scored and ranked leading to a small number of shared, human-understandable concepts that closely describe the target feature. FALCON also applies contrastive interpretation using lowly activating (counterfactual) images, to eliminate spurious concepts. Although many existing approaches interpret features independently, we observe in state-of-the-art self-supervised and supervised models, that less than 20% of the representation space can be explained by individual features. We show that features in larger spaces become more interpretable when studied in groups and can be explained with high-order scoring concepts through FALCON. We discuss how extracted concepts can be used to explain and debug failures in downstream tasks. Finally, we present a technique to transfer concepts from one (explainable) representation space to another unseen representation space by learning a simple linear transformation.

Details

TMLR Journal 2023 Journal Article

Interpretable Mixture of Experts

  • Aya Abdelsalam Ismail
  • Sercan O Arik
  • Jinsung Yoon
  • Ankur Taly
  • Soheil Feizi
  • Tomas Pfister

The need for reliable model explanations is prominent for many machine learning applications, particularly for tabular and time-series data as their use cases often involve high-stakes decision making. Towards this goal, we introduce a novel interpretable modeling framework, Interpretable Mixture of Experts (IME), that yields high accuracy, comparable to `black-box' Deep Neural Networks (DNNs) in many cases, along with useful interpretability capabilities. IME consists of an assignment module and a mixture of experts, with each sample being assigned to a single expert for prediction. We introduce multiple options for IME based on the assignment and experts being interpretable. When the experts are chosen to be interpretable such as linear models, IME yields an inherently-interpretable architecture where the explanations produced by IME are the exact descriptions of how the prediction is computed. In addition to constituting a standalone inherently-interpretable architecture, IME has the premise of being integrated with existing DNNs to offer interpretability to a subset of samples while maintaining the accuracy of the DNNs. Through extensive experiments on 15 tabular and time-series datasets, IME is demonstrated to be more accurate than single interpretable models and perform comparably with existing state-of-the-art DNNs in accuracy. On most datasets, IME even outperforms DNNs, while providing faithful explanations. Lastly, IME's explanations are compared to commonly-used post-hoc explanations methods through a user study -- participants are able to better predict the model behavior when given IME explanations, while finding IME's explanations more faithful and trustworthy.

PDF Details

ICLR Conference 2023 Conference Paper

Provable Robustness against Wasserstein Distribution Shifts via Input Randomization

  • Aounon Kumar
  • Alexander Levine 0001
  • Tom Goldstein
  • Soheil Feizi

Certified robustness in machine learning has primarily focused on adversarial perturbations with a fixed attack budget for each sample in the input distribution. In this work, we present provable robustness guarantees on the accuracy of a model under bounded Wasserstein shifts of the data distribution. We show that a simple procedure that randomizes the input of the model within a transformation space is provably robust to distributional shifts under that transformation. Our framework allows the datum-specific perturbation size to vary across different points in the input distribution and is general enough to include fixed-sized perturbations as well. Our certificates produce guaranteed lower bounds on the performance of the model for any shift (natural or adversarial) of the input distribution within a Wasserstein ball around the original distribution. We apply our technique to certify robustness against natural (non-adversarial) transformations of images such as color shifts, hue shifts, and changes in brightness and saturation. We obtain strong performance guarantees for the robust model under clearly visible shifts in the input images. Our experiments establish the non-vacuousness of our certificates by showing that the certified lower bound on a robust model's accuracy is higher than the empirical accuracy of an undefended model under a distribution shift. Moreover, our results also imply guaranteed lower bounds (hardness result) on the performance of models trained on so-called "unlearnable" datasets that have been poisoned to interfere with model training. We show that the performance of a robust model is guaranteed to remain above a certain threshold on the test distribution even when the base model is trained on the poisoned dataset.

Details

ICML Conference 2023 Conference Paper

Run-off Election: Improved Provable Defense against Data Poisoning Attacks

  • Keivan Rezaei
  • Kiarash Banihashem
  • Atoosa Malemir Chegini
  • Soheil Feizi

In data poisoning attacks, an adversary tries to change a model’s prediction by adding, modifying, or removing samples in the training data. Recently, ensemble-based approaches for obtaining provable defenses against data poisoning have been proposed where predictions are done by taking a majority vote across multiple base models. In this work, we show that merely considering the majority vote in ensemble defenses is wasteful as it does not effectively utilize available information in the logits layers of the base models. Instead, we propose Run-Off Election (ROE), a novel aggregation method based on a two-round election across the base models: In the first round, models vote for their preferred class and then a second, Run-Off election is held between the top two classes in the first round. Based on this approach, we propose DPA+ROE and FA+ROE defense methods based on Deep Partition Aggregation (DPA) and Finite Aggregation (FA) approaches from prior work. We evaluate our methods on MNIST, CIFAR-10, and GTSRB and obtain improvements in certified accuracy by up to $3%$-$4%$. Also, by applying ROE on a boosted version of DPA, we gain improvements around $12%$-$27%$ comparing to the current state-of-the-art, establishing a new state-of-the-art in (pointwise) certified robustness against data poisoning. In many cases, our approach outperforms the state-of-the-art, even when using 32 times less computational power.

Details

NeurIPS Conference 2023 Conference Paper

Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases

  • Mazda Moayeri
  • Wenxiao Wang
  • Sahil Singla
  • Soheil Feizi

We present a simple but effective method to measure and mitigate model biases caused by reliance on spurious cues. Instead of requiring costly changes to one's data or model training, our method better utilizes the data one already has by sorting them. Specifically, we rank images within their classes based on spuriosity (the degree to which common spurious cues are present), proxied via deep neural features of an interpretable network. With spuriosity rankings, it is easy to identify minority subpopulations (i. e. low spuriosity images) and assess model bias as the gap in accuracy between high and low spuriosity images. One can even efficiently remove a model's bias at little cost to accuracy by finetuning its classification head on low spuriosity images, resulting in fairer treatment of samples regardless of spuriosity. We demonstrate our method on ImageNet, annotating $5000$ class-feature dependencies ($630$ of which we find to be spurious) and generating a dataset of $325k$ soft segmentations for these features along the way. Having computed spuriosity rankings via the identified spurious neural features, we assess biases for $89$ diverse models and find that class-wise biases are highly correlated across models. Our results suggest that model bias due to spurious feature reliance is influenced far more by what the model is trained on than how it is trained.

PDF Details

NeurIPS Conference 2023 Conference Paper

Temporal Robustness against Data poisoning

  • Wenxiao Wang
  • Soheil Feizi

Data poisoning considers cases when an adversary manipulates the behavior of machine learning algorithms through malicious training data. Existing threat models of data poisoning center around a single metric, the number of poisoned samples. In consequence, if attackers can poison more samples than expected with affordable overhead, as in many practical scenarios, they may be able to render existing defenses ineffective in a short time. To address this issue, we leverage timestamps denoting the birth dates of data, which are often available but neglected in the past. Benefiting from these timestamps, we propose a temporal threat model of data poisoning with two novel metrics, earliness and duration, which respectively measure how long an attack started in advance and how long an attack lasted. Using these metrics, we define the notions of temporal robustness against data poisoning, providing a meaningful sense of protection even with unbounded amounts of poisoned samples when the attacks are temporally bounded. We present a benchmark with an evaluation protocol simulating continuous data collection and periodic deployments of updated models, thus enabling empirical evaluation of temporal robustness. Lastly, we develop and also empirically verify a baseline defense, namely temporal aggregation, offering provable temporal robustness and highlighting the potential of our temporal threat model for data poisoning.

PDF Details

ICML Conference 2023 Conference Paper

Text-To-Concept (and Back) via Cross-Model Alignment

  • Mazda Moayeri
  • Keivan Rezaei
  • Maziar Sanjabi
  • Soheil Feizi

We observe that the mapping between an image’s representation in one model to its representation in another can be learned surprisingly well with just a linear layer, even across diverse models. Building on this observation, we propose text-to-concept, where features from a fixed pretrained model are aligned linearly to the CLIP space, so that text embeddings from CLIP’s text encoder become directly comparable to the aligned features. With text-to-concept, we convert fixed off-the-shelf vision encoders to surprisingly strong zero-shot classifiers for free, with accuracy at times even surpassing that of CLIP, despite being much smaller models and trained on a small fraction of the data compared to CLIP. We show other immediate use-cases of text-to-concept, like building concept bottleneck models with no concept supervision, diagnosing distribution shifts in terms of human concepts, and retrieving images satisfying a set of text-based constraints. Lastly, we demonstrate the feasibility of concept-to-text, where vectors in a model’s feature space are decoded by first aligning to the CLIP before being fed to a GPT-based generative model. Our work suggests existing deep models, with presumably diverse architectures and training, represent input samples relatively similarly, and a two-way communication across model representation spaces and to humans (through language) is viable.

Details

NeurIPS Conference 2022 Conference Paper

Explicit Tradeoffs between Adversarial and Natural Distributional Robustness

  • Mazda Moayeri
  • Kiarash Banihashem
  • Soheil Feizi

Several existing works study either adversarial or natural distributional robustness of deep neural networks separately. In practice, however, models need to enjoy both types of robustness to ensure reliability. In this work, we bridge this gap and show that in fact, {\it explicit tradeoffs} exist between adversarial and natural distributional robustness. We first consider a simple linear regression setting on Gaussian data with disjoint sets of \emph{core} and \emph{spurious} features. In this setting, through theoretical and empirical analysis, we show that (i) adversarial training with $\ell_1$ and $\ell_2$ norms increases the model reliance on spurious features; (ii) For $\ell_\infty$ adversarial training, spurious reliance only occurs when the scale of the spurious features is larger than that of the core features; (iii) adversarial training can have {\it an unintended consequence} in reducing distributional robustness, specifically when spurious correlations are changed in the new test domain. Next, we present extensive empirical evidence, using a test suite of twenty adversarially trained models evaluated on five benchmark datasets (ObjectNet, RIVAL10, Salient ImageNet-1M, ImageNet-9, Waterbirds), that adversarially trained classifiers rely on backgrounds more than their standardly trained counterparts, validating our theoretical results. We also show that spurious correlations in training data (when preserved in the test domain) can {\it improve} adversarial robustness, revealing that previous claims that adversarial vulnerability is rooted in spurious correlations are incomplete.

PDF Details

ICML Conference 2022 Conference Paper

FOCUS: Familiar Objects in Common and Uncommon Settings

  • Priyatham Kattakinda
  • Soheil Feizi

Standard training datasets for deep learning often do not contain objects in uncommon and rare settings (e. g. , “a plane on water”, “a car in snowy weather”). This can cause models trained on these datasets to incorrectly predict objects that are typical for the context in the image, rather than identifying the objects that are actually present. In this paper, we introduce FOCUS (Familiar Objects in Common and Uncommon Settings), a dataset for stress-testing the generalization power of deep image classifiers. By leveraging the power of modern search engines, we deliberately gather data containing objects in common and uncommon settings; in a wide range of locations, weather conditions, and time of day. We present a detailed analysis of the performance of various popular image classifiers on our dataset and demonstrate a clear drop in accuracy when classifying images in uncommon settings. We also show that finetuning a model on our dataset drastically improves its ability to focus on the object of interest leading to better generalization. Lastly, we leverage FOCUS to machine annotate additional visual attributes for the entirety of ImageNet. We believe that our dataset will aid researchers in understanding the inability of deep models to generalize well to uncommon settings and drive future work on improving their distributional robustness.

Details

NeurIPS Conference 2022 Conference Paper

Hard ImageNet: Segmentations for Objects with Strong Spurious Cues

  • Mazda Moayeri
  • Sahil Singla
  • Soheil Feizi

Deep classifiers are known to rely on spurious features, leading to reduced generalization. The severity of this problem varies significantly by class. We identify $15$ classes in ImageNet with very strong spurious cues, and collect segmentation masks for these challenging objects to form \emph{Hard ImageNet}. Leveraging noise, saliency, and ablation based metrics, we demonstrate that models rely on spurious features in Hard ImageNet far more than in RIVAL10, an ImageNet analog to CIFAR10. We observe Hard ImageNet objects are less centered and occupy much less space in their images than RIVAL10 objects, leading to greater spurious feature reliance. Further, we use robust neural features to automatically rank our images based on the degree of spurious cues present. Comparing images with high and low rankings within a class reveals the exact spurious features models rely upon, and shows reduced performance when spurious features are absent. With Hard ImageNet's image rankings, object segmentations, and our extensive evaluation suite, the community can begin to address the problem of learning to detect challenging objects \emph{for the right reasons}, despite the presence of strong spurious cues.

PDF Details

ICML Conference 2022 Conference Paper

Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation

  • Wenxiao Wang 0002
  • Alexander Levine 0001
  • Soheil Feizi

Data poisoning attacks aim at manipulating model behaviors through distorting training data. Previously, an aggregation-based certified defense, Deep Partition Aggregation (DPA), was proposed to mitigate this threat. DPA predicts through an aggregation of base classifiers trained on disjoint subsets of data, thus restricting its sensitivity to dataset distortions. In this work, we propose an improved certified defense against general poisoning attacks, namely Finite Aggregation. In contrast to DPA, which directly splits the training set into disjoint subsets, our method first splits the training set into smaller disjoint subsets and then combines duplicates of them to build larger (but not disjoint) subsets for training base classifiers. This reduces the worst-case impacts of poison samples and thus improves certified robustness bounds. In addition, we offer an alternative view of our method, bridging the designs of deterministic and stochastic aggregation-based certified defenses. Empirically, our proposed Finite Aggregation consistently improves certificates on MNIST, CIFAR-10, and GTSRB, boosting certified fractions by up to 3. 05%, 3. 87% and 4. 77%, respectively, while keeping the same clean accuracies as DPA’s, effectively establishing a new state of the art in (pointwise) certified robustness against data poisoning.

Details

ICLR Conference 2022 Conference Paper

Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100

  • Sahil Singla 0002
  • Surbhi Singla
  • Soheil Feizi

Training convolutional neural networks (CNNs) with a strict Lipschitz constraint under the $l_{2}$ norm is useful for provable adversarial robustness, interpretable gradients and stable training. While $1$-Lipschitz CNNs can be designed by enforcing a $1$-Lipschitz constraint on each layer, training such networks requires each layer to have an orthogonal Jacobian matrix (for all inputs) to prevent the gradients from vanishing during backpropagation. A layer with this property is said to be Gradient Norm Preserving (GNP). In this work, we introduce a procedure to certify the robustness of $1$-Lipschitz CNNs by relaxing the orthogonalization of the last linear layer of the network that significantly advances the state of the art for both standard and provable robust accuracies on CIFAR-100 (gains of $4.80\%$ and $4.71\%$, respectively). We further boost their robustness by introducing (i) a novel Gradient Norm preserving activation function called the Householder activation function (that includes every $\mathrm{GroupSort}$ activation) and (ii) a certificate regularization. On CIFAR-10, we achieve significant improvements over prior works in provable robust accuracy ($5.81\%$) with only a minor drop in standard accuracy ($-0.29\%$). Code for reproducing all experiments in the paper is available at \url{https://github.com/singlasahil14/SOC}.

Details

NeurIPS Conference 2022 Conference Paper

Improved techniques for deterministic l2 robustness

  • Sahil Singla
  • Soheil Feizi

Training convolutional neural networks (CNNs) with a strict 1-Lipschitz constraint under the l_{2} norm is useful for adversarial robustness, interpretable gradients and stable training. 1-Lipschitz CNNs are usually designed by enforcing each layer to have an orthogonal Jacobian matrix (for all inputs) to prevent the gradients from vanishing during backpropagation. However, their performance often significantly lags behind that of heuristic methods to enforce Lipschitz constraints where the resulting CNN is not provably 1-Lipschitz. In this work, we reduce this gap by introducing (a) a procedure to certify robustness of 1-Lipschitz CNNs by replacing the last linear layer with a 1-hidden layer MLP that significantly improves their performance for both standard and provably robust accuracy, (b) a method to significantly reduce the training time per epoch for Skew Orthogonal Convolution (SOC) layers (>30\% reduction for deeper networks) and (c) a class of pooling layers using the mathematical property that the l_{2} distance of an input to a manifold is 1-Lipschitz. Using these methods, we significantly advance the state-of-the-art for standard and provable robust accuracies on CIFAR-10 (gains of +1. 79\% and +3. 82\%) and similarly on CIFAR-100 (+3. 78\% and +4. 75\% across all networks.

PDF Details

NeurIPS Conference 2022 Conference Paper

Lethal Dose Conjecture on Data Poisoning

  • Wenxiao Wang
  • Alexander Levine
  • Soheil Feizi

Data poisoning considers an adversary that distorts the training set of machine learning algorithms for malicious purposes. In this work, we bring to light one conjecture regarding the fundamentals of data poisoning, which we call the Lethal Dose Conjecture. The conjecture states: If $n$ clean training samples are needed for accurate predictions, then in a size-$N$ training set, only $\Theta(N/n)$ poisoned samples can be tolerated while ensuring accuracy. Theoretically, we verify this conjecture in multiple cases. We also offer a more general perspective of this conjecture through distribution discrimination. Deep Partition Aggregation (DPA) and its extension, Finite Aggregation (FA) are recent approaches for provable defenses against data poisoning, where they predict through the majority vote of many base models trained from different subsets of training set using a given learner. The conjecture implies that both DPA and FA are (asymptotically) optimal---if we have the most data-efficient learner, they can turn it into one of the most robust defenses against data poisoning. This outlines a practical approach to developing stronger defenses against poisoning via finding data-efficient learners. Empirically, as a proof of concept, we show that by simply using different data augmentations for base learners, we can respectively double and triple the certified robustness of DPA on CIFAR-10 and GTSRB without sacrificing accuracy.

PDF Details

ICLR Conference 2022 Conference Paper

Policy Smoothing for Provably Robust Reinforcement Learning

  • Aounon Kumar
  • Alexander Levine 0001
  • Soheil Feizi

The study of provable adversarial robustness for deep neural networks (DNNs) has mainly focused on $\textit{static}$ supervised learning tasks such as image classification. However, DNNs have been used extensively in real-world $\textit{adaptive}$ tasks such as reinforcement learning (RL), making such systems vulnerable to adversarial attacks as well. Prior works in provable robustness in RL seek to certify the behaviour of the victim policy at every time-step against a non-adaptive adversary using methods developed for the static setting. But in the real world, an RL adversary can infer the defense strategy used by the victim agent by observing the states, actions, etc. from previous time-steps and adapt itself to produce stronger attacks in future steps (e.g., by focusing more on states critical to the agent's performance). We present an efficient procedure, designed specifically to defend against an adaptive RL adversary, that can directly certify the total reward without requiring the policy to be robust at each time-step. Focusing on randomized smoothing based defenses, our main theoretical contribution is to prove an $\textit{adaptive version}$ of the Neyman-Pearson Lemma -- a key lemma for smoothing-based certificates -- where the adversarial perturbation at a particular time can be a stochastic function of current and previous observations and states as well as previous actions. Building on this result, we propose $\textit{policy smoothing}$ where the agent adds a Gaussian noise to its observation at each time-step before passing it through the policy function. Our robustness certificates guarantee that the final total reward obtained by policy smoothing remains above a certain threshold, even though the actions at intermediate time-steps may change under the attack. We show that our certificates are $\textit{tight}$ by constructing a worst-case scenario that achieves the bounds derived in our analysis. Our experiments on various environments like Cartpole, Pong, Freeway and Mountain Car show that our method can yield meaningful robustness guarantees in practice.

Details

ICLR Conference 2022 Conference Paper

Salient ImageNet: How to discover spurious features in Deep Learning?

  • Sahil Singla 0002
  • Soheil Feizi

Deep neural networks can be unreliable in the real world especially when they heavily use {\it spurious} features for their predictions. Focusing on image classifications, we define {\it core features} as the set of visual features that are always a part of the object definition while {\it spurious features} are the ones that are likely to {\it co-occur} with the object but not a part of it (e.g., attribute ``fingers" for class ``band aid"). Traditional methods for discovering spurious features either require extensive human annotations (thus, not scalable), or are useful on specific models. In this work, we introduce a {\it general} framework to discover a subset of spurious and core visual features used in inferences of a general model and localize them on a large number of images with minimal human supervision. Our methodology is based on this key idea: to identify spurious or core \textit{visual features} used in model predictions, we identify spurious or core \textit{neural features} (penultimate layer neurons of a robust model) via limited human supervision (e.g., using top 5 activating images per feature). We then show that these neural feature annotations {\it generalize} extremely well to many more images {\it without} any human supervision. We use the activation maps for these neural features as the soft masks to highlight spurious or core visual features. Using this methodology, we introduce the {\it Salient Imagenet} dataset containing core and spurious masks for a large set of samples from Imagenet. Using this dataset, we show that several popular Imagenet models rely heavily on various spurious features in their predictions, indicating the standard accuracy alone is not sufficient to fully assess model' performance specially in safety-critical applications. Code is available at \url{https://github.com/singlasahil14/salient_imagenet}.

Details

NeurIPS Conference 2022 Conference Paper

Toward Efficient Robust Training against Union of $\ell_p$ Threat Models

  • Gaurang Sriramanan
  • Maharshi Gor
  • Soheil Feizi

The overwhelming vulnerability of deep neural networks to carefully crafted perturbations known as adversarial attacks has led to the development of various training techniques to produce robust models. While the primary focus of existing approaches has been directed toward addressing the worst-case performance achieved under a single-threat model, it is imperative that safety-critical systems are robust with respect to multiple threat models simultaneously. Existing approaches that address worst-case performance under the union of such threat models ($\ell_{\infty}, \ell_2, \ell_1$) either utilize adversarial training methods that require multi-step attacks which are computationally expensive in practice, or rely upon fine-tuning of pre-trained models that are robust with respect to a single-threat model. In this work, we show that by carefully choosing the objective function used for robust training, it is possible to achieve similar, or improved worst-case performance over a union of threat models while utilizing only single-step attacks, thereby achieving a significant reduction in computational resources necessary for training. Furthermore, prior work showed that adversarial training specific to the $\ell_1$ threat model is relatively difficult, to the extent that even multi-step adversarially trained models were shown to be prone to gradient-masking. However, the proposed method—when applied on the $\ell_1$ threat model specifically—enables us to obtain the first $\ell_1$ robust model trained solely with single-step adversaries. Finally, to demonstrate the merits of our approach, we utilize a modern set of attack evaluations to better estimate the worst-case performance under the considered union of threat models.

PDF Details

ICLR Conference 2021 Conference Paper

Deep Partition Aggregation: Provable Defenses against General Poisoning Attacks

  • Alexander Levine 0001
  • Soheil Feizi

Adversarial poisoning attacks distort training data in order to corrupt the test-time behavior of a classifier. A provable defense provides a certificate for each test sample, which is a lower bound on the magnitude of any adversarial distortion of the training set that can corrupt the test sample's classification. We propose two novel provable defenses against poisoning attacks: (i) Deep Partition Aggregation (DPA), a certified defense against a general poisoning threat model, defined as the insertion or deletion of a bounded number of samples to the training set --- by implication, this threat model also includes arbitrary distortions to a bounded number of images and/or labels; and (ii) Semi-Supervised DPA (SS-DPA), a certified defense against label-flipping poisoning attacks. DPA is an ensemble method where base models are trained on partitions of the training set determined by a hash function. DPA is related to both subset aggregation, a well-studied ensemble method in classical machine learning, as well as to randomized smoothing, a popular provable defense against evasion (inference) attacks. Our defense against label-flipping poison attacks, SS-DPA, uses a semi-supervised learning algorithm as its base classifier model: each base classifier is trained using the entire unlabeled training set in addition to the labels for a partition. SS-DPA significantly outperforms the existing certified defense for label-flipping attacks (Rosenfeld et al., 2020) on both MNIST and CIFAR-10: provably tolerating, for at least half of test images, over 600 label flips (vs. < 200 label flips) on MNIST and over 300 label flips (vs. 175 label flips) on CIFAR-10. Against general poisoning attacks where no prior certified defenses exists, DPA can certify $\geq$ 50% of test images against over 500 poison image insertions on MNIST, and nine insertions on CIFAR-10. These results establish new state-of-the-art provable defenses against general and label-flipping poison attacks. Code is available at https://github.com/alevine0/DPA

Details

ICLR Conference 2021 Conference Paper

Fantastic Four: Differentiable and Efficient Bounds on Singular Values of Convolution Layers

  • Sahil Singla 0002
  • Soheil Feizi

In deep neural networks, the spectral norm of the Jacobian of a layer bounds the factor by which the norm of a signal changes during forward/backward propagation. Spectral norm regularizations have been shown to improve generalization, robustness and optimization of deep learning methods. Existing methods to compute the spectral norm of convolution layers either rely on heuristics that are efficient in computation but lack guarantees or are theoretically-sound but computationally expensive. In this work, we obtain the best of both worlds by deriving {\it four} provable upper bounds on the spectral norm of a standard 2D multi-channel convolution layer. These bounds are differentiable and can be computed efficiently during training with negligible overhead. One of these bounds is in fact the popular heuristic method of Miyato et al. (multiplied by a constant factor depending on filter sizes). Each of these four bounds can achieve the tightest gap depending on convolution filters. Thus, we propose to use the minimum of these four bounds as a tight, differentiable and efficient upper bound on the spectral norm of convolution layers. Moreover, our spectral bound is an effective regularizer and can be used to bound either the lipschitz constant or curvature values (eigenvalues of the Hessian) of neural networks. Through experiments on MNIST and CIFAR-10, we demonstrate the effectiveness of our spectral bound in improving generalization and robustness of deep networks.

Details

ICML Conference 2021 Conference Paper

Improved, Deterministic Smoothing for L 1 Certified Robustness

  • Alexander Levine 0001
  • Soheil Feizi

Randomized smoothing is a general technique for computing sample-dependent robustness guarantees against adversarial attacks for deep classifiers. Prior works on randomized smoothing against L_1 adversarial attacks use additive smoothing noise and provide probabilistic robustness guarantees. In this work, we propose a non-additive and deterministic smoothing method, Deterministic Smoothing with Splitting Noise (DSSN). To develop DSSN, we first develop SSN, a randomized method which involves generating each noisy smoothing sample by first randomly splitting the input space and then returning a representation of the center of the subdivision occupied by the input sample. In contrast to uniform additive smoothing, the SSN certification does not require the random noise components used to be independent. Thus, smoothing can be done effectively in just one dimension and can therefore be efficiently derandomized for quantized data (e. g. , images). To the best of our knowledge, this is the first work to provide deterministic "randomized smoothing" for a norm-based adversarial threat model while allowing for an arbitrary classifier (i. e. , a deep model) to be used as a base classifier and without requiring an exponential number of smoothing samples. On CIFAR-10 and ImageNet datasets, we provide substantially larger L_1 robustness certificates compared to prior works, establishing a new state-of-the-art. The determinism of our method also leads to significantly faster certificate computation. Code is available at: https: //github. com/alevine0/smoothingSplittingNoise.

Details

NeurIPS Conference 2021 Conference Paper

Improving Deep Learning Interpretability by Saliency Guided Training

  • Aya Abdelsalam Ismail
  • Hector Corrada Bravo
  • Soheil Feizi

Saliency methods have been widely used to highlight important input features in model predictions. Most existing methods use backpropagation on a modified gradient function to generate saliency maps. Thus, noisy gradients can result in unfaithful feature attributions. In this paper, we tackle this issue and introduce a {\it saliency guided training} procedure for neural networks to reduce noisy gradients used in predictions while retaining the predictive performance of the model. Our saliency guided training procedure iteratively masks features with small and potentially noisy gradients while maximizing the similarity of model outputs for both masked and unmasked inputs. We apply the saliency guided training procedure to various synthetic and real data sets from computer vision, natural language processing, and time series across diverse neural architectures, including Recurrent Neural Networks, Convolutional Networks, and Transformers. Through qualitative and quantitative evaluations, we show that saliency guided training procedure significantly improves model interpretability across various domains while preserving its predictive performance.

PDF Details

ICLR Conference 2021 Conference Paper

Influence Functions in Deep Learning Are Fragile

  • Samyadeep Basu
  • Phillip Pope
  • Soheil Feizi

Influence functions approximate the effect of training samples in test-time predictions and have a wide variety of applications in machine learning interpretability and uncertainty estimation. A commonly-used (first-order) influence function can be implemented efficiently as a post-hoc method requiring access only to the gradients and Hessian of the model. For linear models, influence functions are well-defined due to the convexity of the underlying loss function and are generally accurate even across difficult settings where model changes are fairly large such as estimating group influences. Influence functions, however, are not well-understood in the context of deep learning with non-convex loss functions. In this paper, we provide a comprehensive and large-scale empirical study of successes and failures of influence functions in neural network models trained on datasets such as Iris, MNIST, CIFAR-10 and ImageNet. Through our extensive experiments, we show that the network architecture, its depth and width, as well as the extent of model parameterization and regularization techniques have strong effects in the accuracy of influence functions. In particular, we find that (i) influence estimates are fairly accurate for shallow networks, while for deeper networks the estimates are often erroneous; (ii) for certain network architectures and datasets, training with weight-decay regularization is important to get high-quality influence estimates; and (iii) the accuracy of influence estimates can vary significantly depending on the examined test points. These results suggest that in general influence functions in deep learning are fragile and call for developing improved influence estimation methods to mitigate these issues in non-convex setups.

Details

ICLR Conference 2021 Conference Paper

Perceptual Adversarial Robustness: Defense Against Unseen Threat Models

  • Cassidy Laidlaw
  • Sahil Singla 0002
  • Soheil Feizi

A key challenge in adversarial robustness is the lack of a precise mathematical characterization of human perception, used in the definition of adversarial attacks that are imperceptible to human eyes. Most current attacks and defenses try to get around this issue by considering restrictive adversarial threat models such as those bounded by $L_2$ or $L_\infty$ distance, spatial perturbations, etc. However, models that are robust against any of these restrictive threat models are still fragile against other threat models, i.e. they have poor generalization to unforeseen attacks. Moreover, even if a model is robust against the union of several restrictive threat models, it is still susceptible to other imperceptible adversarial examples that are not contained in any of the constituent threat models. To resolve these issues, we propose adversarial training against the set of all imperceptible adversarial examples. Since this set is intractable to compute without a human in the loop, we approximate it using deep neural networks. We call this threat model the neural perceptual threat model (NPTM); it includes adversarial examples with a bounded neural perceptual distance (a neural network-based approximation of the true perceptual distance) to natural images. Through an extensive perceptual study, we show that the neural perceptual distance correlates well with human judgements of perceptibility of adversarial examples, validating our threat model. Under the NPTM, we develop novel perceptual adversarial attacks and defenses. Because the NPTM is very broad, we find that Perceptual Adversarial Training (PAT) against a perceptual attack gives robustness against many other types of adversarial attacks. We test PAT on CIFAR-10 and ImageNet-100 against five diverse adversarial attacks: $L_2$, $L_\infty$, spatial, recoloring, and JPEG. We find that PAT achieves state-of-the-art robustness against the union of these five attacks—more than doubling the accuracy over the next best model—without training against any of them. That is, PAT generalizes well to unforeseen perturbation types. This is vital in sensitive applications where a particular threat model cannot be assumed, and to the best of our knowledge, PAT is the first adversarial training defense with this property. Code and data are available at https://github.com/cassidylaidlaw/perceptual-advex

Details

ICML Conference 2021 Conference Paper

Skew Orthogonal Convolutions

  • Sahil Singla 0002
  • Soheil Feizi

Training convolutional neural networks with a Lipschitz constraint under the $l_{2}$ norm is useful for provable adversarial robustness, interpretable gradients, stable training, etc. While 1-Lipschitz networks can be designed by imposing a 1-Lipschitz constraint on each layer, training such networks requires each layer to be gradient norm preserving (GNP) to prevent gradients from vanishing. However, existing GNP convolutions suffer from slow training, lead to significant reduction in accuracy and provide no guarantees on their approximations. In this work, we propose a GNP convolution layer called \textbf{S}kew \textbf{O}rthogonal \textbf{C}onvolution (SOC) that uses the following mathematical property: when a matrix is {\it Skew-Symmetric}, its exponential function is an {\it orthogonal} matrix. To use this property, we first construct a convolution filter whose Jacobian is Skew-Symmetric. Then, we use the Taylor series expansion of the Jacobian exponential to construct the SOC layer that is orthogonal. To efficiently implement SOC, we keep a finite number of terms from the Taylor series and provide a provable guarantee on the approximation error. Our experiments on CIFAR-10 and CIFAR-100 show that SOC allows us to train provably Lipschitz, large convolutional neural networks significantly faster than prior works while achieving significant improvements for both standard and certified robust accuracies.

Details

ICLR Conference 2021 Conference Paper

Understanding Over-parameterization in Generative Adversarial Networks

  • Yogesh Balaji
  • Mohammadmahdi Sajedi
  • Neha Mukund Kalibhat
  • Mucong Ding
  • Dominik Stöger
  • Mahdi Soltanolkotabi
  • Soheil Feizi

A broad class of unsupervised deep learning methods such as Generative Adversarial Networks (GANs) involve training of overparameterized models where the number of parameters of the model exceeds a certain threshold. Indeed, most successful GANs used in practice are trained using overparameterized generator and discriminator networks, both in terms of depth and width. A large body of work in supervised learning have shown the importance of model overparameterization in the convergence of the gradient descent (GD) to globally optimal solutions. In contrast, the unsupervised setting and GANs in particular involve non-convex concave mini-max optimization problems that are often trained using Gradient Descent/Ascent (GDA). The role and benefits of model overparameterization in the convergence of GDA to a global saddle point in non-convex concave problems is far less understood. In this work, we present a comprehensive analysis of the importance of model overparameterization in GANs both theoretically and empirically. We theoretically show that in an overparameterized GAN model with a $1$-layer neural network generator and a linear discriminator, GDA converges to a global saddle point of the underlying non-convex concave min-max problem. To the best of our knowledge, this is the first result for global convergence of GDA in such settings. Our theory is based on a more general result that holds for a broader class of nonlinear generators and discriminators that obey certain assumptions (including deeper generators and random feature discriminators). Our theory utilizes and builds upon a novel connection with the convergence analysis of linear time-varying dynamical systems which may have broader implications for understanding the convergence behavior of GDA for non-convex concave problems involving overparameterized models. We also empirically study the role of model overparameterization in GANs using several large-scale experiments on CIFAR-10 and Celeb-A datasets. Our experiments show that overparameterization improves the quality of generated samples across various model architectures and datasets. Remarkably, we observe that overparameterization leads to faster and more stable convergence behavior of GDA across the board.

Details

UAI Conference 2021 Conference Paper

Unsupervised anomaly detection with adversarial mirrored autoencoders

  • Gowthami Somepalli
  • Yexin Wu
  • Yogesh Balaji
  • Bhanukiran Vinzamuri
  • Soheil Feizi

Detecting out-of-distribution (OOD) samples is of paramount importance in all Machine Learning applications. Deep generative modeling has emerged as a dominant paradigm to model complex data distributions without labels. However, prior work has shown that generative models tend to assign higher likelihoods to OOD samples compared to the data distribution on which they were trained. First, we propose Adversarial Mirrored Autoencoder (AMA), a variant of Adversarial Autoencoder, which uses a mirrored Wasserstein loss in the discriminator to enforce better semantic-level reconstruction. We also propose a latent space regularization to learn a compact manifold for in-distribution samples. The use of AMA produces better feature representations that improve anomaly detection performance. Second, we put forward an alternative measure of anomaly score to replace the reconstruction-based metric which has been traditionally used in generative model-based anomaly detection methods. Our method outperforms the current state-of-the-art methods for anomaly detection on several OOD detection benchmarks.

Details

AAAI Conference 2021 Conference Paper

Winning Lottery Tickets in Deep Generative Models

  • Neha Mukund Kalibhat
  • Yogesh Balaji
  • Soheil Feizi

The lottery ticket hypothesis suggests that sparse, subnetworks of a given neural network, if initialized properly, can be trained to reach comparable or even better performance to that of the original network. Prior works in lottery tickets have primarily focused on the supervised learning setup, with several papers proposing effective ways of finding winning tickets in classification problems. In this paper, we confirm the existence of winning tickets in deep generative models such as GANs and VAEs. We show that the popular iterative magnitude pruning approach (with late resetting) can be used with generative losses to find the winning tickets. This approach effectively yields tickets with sparsity up to 99% for AutoEncoders, 93% for VAEs and 89% for GANs on CIFAR and Celeb-A datasets. We also demonstrate the transferability of winning tickets across different generative models (GANs and VAEs) sharing the same architecture, suggesting that winning tickets have inductive biases that could help train a wide range of deep generative models. Furthermore, we show the practical benefits of lottery tickets in generative models by detecting tickets at very early stages in training called early-bird tickets. Through early-bird tickets, we can achieve up to 88% reduction in floating-point operations (FLOPs) and 54% reduction in training time, making it possible to train large-scale generative models over tight resource constraints. These results out-perform existing early pruning methods like SNIP (Lee, Ajanthan, and Torr 2019) and GraSP (Wang, Zhang, and Grosse 2020). Our findings shed light towards existence of proper network initializations that could improve convergence and stability of generative models.

PDF Details

NeurIPS Conference 2020 Conference Paper

(De)Randomized Smoothing for Certifiable Defense against Patch Attacks

  • Alexander Levine
  • Soheil Feizi

Patch adversarial attacks on images, in which the attacker can distort pixels within a region of bounded size, are an important threat model since they provide a quantitative model for physical adversarial attacks. In this paper, we introduce a certifiable defense against patch attacks that guarantees for a given image and patch attack size, no patch adversarial examples exist. Our method is related to the broad class of randomized smoothing robustness schemes which provide high-confidence probabilistic robustness certificates. By exploiting the fact that patch attacks are more constrained than general sparse attacks, we derive meaningfully large robustness certificates against them. Additionally, in contrast to smoothing-based defenses against L_p and sparse attacks, our defense method against patch attacks is de-randomized, yielding improved, deterministic certificates. Compared to the existing patch certification method proposed by (Chiang et al. , 2020), which relies on interval bound propagation, our method can be trained significantly faster, achieves high clean and certified robust accuracy on CIFAR-10, and provides certificates at ImageNet scale. For example, for a 5-by-5 patch attack on CIFAR-10, our method achieves up to around 57. 6% certified accuracy (with a classifier with around 83. 8% clean accuracy), compared to at most 30. 3% certified accuracy for the existing method (with a classifier with around 47. 8% clean accuracy). Our results effectively establish a new state-of-the-art of certifiable defense against patch attacks on CIFAR-10 and ImageNet.

PDF Details

AAAI Conference 2020 Conference Paper

Adversarially Robust Distillation

  • Micah Goldblum
  • Liam Fowl
  • Soheil Feizi
  • Tom Goldstein

Knowledge distillation is effective for producing small, highperformance neural networks for classification, but these small networks are vulnerable to adversarial attacks. This paper studies how adversarial robustness transfers from teacher to student during knowledge distillation. We find that a large amount of robustness may be inherited by the student even when distilled on only clean images. Second, we introduce Adversarially Robust Distillation (ARD) for distilling robustness onto student networks. In addition to producing small models with high test accuracy like conventional distillation, ARD also passes the superior robustness of large networks onto the student. In our experiments, we find that ARD student models decisively outperform adversarially trained networks of identical architecture in terms of robust accuracy, surpassing state-of-the-art methods on standard robustness benchmarks. Finally, we adapt recent fast adversarial training methods to ARD for accelerated robust distillation.

PDF Details

NeurIPS Conference 2020 Conference Paper

Benchmarking Deep Learning Interpretability in Time Series Predictions

  • Aya Abdelsalam Ismail
  • Mohamed Gunady
  • Hector Corrada Bravo
  • Soheil Feizi

Saliency methods are used extensively to highlight the importance of input features in model predictions. These methods are mostly used in vision and language tasks, and their applications to time series data is relatively unexplored. In this paper, we set out to extensively compare the performance of various saliency-based interpretability methods across diverse neural architectures, including Recurrent Neural Network, Temporal Convolutional Networks, and Transformers in a new benchmark of synthetic time series data. We propose and report multiple metrics to empirically evaluate the performance of saliency methods for detecting feature importance over time using both precision (i. e. , whether identified features contain meaningful signals) and recall (i. e. , the number of features with signal identified as important). Through several experiments, we show that (i) in general, network architectures and saliency methods fail to reliably and accurately identify feature importance over time in time series data, (ii) this failure is mainly due to the conflation of time and feature domains, and (iii) the quality of saliency maps can be improved substantially by using our proposed two-step temporal saliency rescaling (TSR) approach that first calculates the importance of each time step before calculating the importance of each feature at a time step.

PDF Details

NeurIPS Conference 2020 Conference Paper

Certifying Confidence via Randomized Smoothing

  • Aounon Kumar
  • Alexander Levine
  • Soheil Feizi
  • Tom Goldstein

Randomized smoothing has been shown to provide good certified-robustness guarantees for high-dimensional classification problems. It uses the probabilities of predicting the top two most-likely classes around an input point under a smoothing distribution to generate a certified radius for a classifier's prediction. However, most smoothing methods do not give us any information about the \emph{confidence} with which the underlying classifier (e. g. , deep neural network) makes a prediction. In this work, we propose a method to generate certified radii for the prediction confidence of the smoothed classifier. We consider two notions for quantifying confidence: average prediction score of a class and the margin by which the average prediction score of one class exceeds that of another. We modify the Neyman-Pearson lemma (a key theorem in randomized smoothing) to design a procedure for computing the certified radius where the confidence is guaranteed to stay above a certain threshold. Our experimental results on CIFAR-10 and ImageNet datasets show that using information about the distribution of the confidence scores allows us to achieve a significantly better certified radius than ignoring it. Thus, we demonstrate that extra information about the base classifier at the input point can help improve certified guarantees for the smoothed classifier. Code for the experiments is available at \url{https: //github. com/aounon/cdf-smoothing}.

PDF Details

ICML Conference 2020 Conference Paper

Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness

  • Aounon Kumar
  • Alexander Levine 0001
  • Tom Goldstein
  • Soheil Feizi

Randomized smoothing, using just a simple isotropic Gaussian distribution, has been shown to produce good robustness guarantees against $\ell_2$-norm bounded adversaries. In this work, we show that extending the smoothing technique to defend against other attack models can be challenging, especially in the high-dimensional regime. In particular, for a vast class of i. i. d. smoothing distributions, we prove that the largest $\ell_p$-radius that can be certified decreases as $O(1/d^{\frac{1}{2} - \frac{1}{p}})$ with dimension $d$ for $p > 2$. Notably, for $p \geq 2$, this dependence on $d$ is no better than that of the $\ell_p$-radius that can be certified using isotropic Gaussian smoothing, essentially putting a matching lower bound on the robustness radius. When restricted to \emph{generalized} Gaussian smoothing, these two bounds can be shown to be within a constant factor of each other in an asymptotic sense, establishing that Gaussian smoothing provides the best possible results, up to a constant factor, when $p \geq 2$. We present experimental results on CIFAR to validate our theory. For other smoothing distributions, such as, a uniform distribution within an $\ell_1$ or an $\ell_\infty$-norm ball, we show upper bounds of the form $O(1 / d)$ and $O(1 / d^{1 - \frac{1}{p}})$ respectively, which have an even worse dependence on $d$.

Details

NeurIPS Conference 2020 Conference Paper

Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks

  • Wei-An Lin
  • Chun Pong Lau
  • Alexander Levine
  • Rama Chellappa
  • Soheil Feizi

Adversarial training is a popular defense strategy against attack threat models with bounded Lp norms. However, it often degrades the model performance on normal images and more importantly, the defense does not generalize well to novel attacks. Given the success of deep generative models such as GANs and VAEs in characterizing the underlying manifold of images, we investigate whether or not the aforementioned deficiencies of adversarial training can be remedied by exploiting the underlying manifold information. To partially answer this question, we consider the scenario when the manifold information of the underlying data is available. We use a subset of ImageNet natural images where an approximate underlying manifold is learned using StyleGAN. We also construct an ``On-Manifold ImageNet'' (OM-ImageNet) dataset by projecting the ImageNet samples onto the learned manifold. For OM-ImageNet, the underlying manifold information is exact. Using OM-ImageNet, we first show that on-manifold adversarial training improves both standard accuracy and robustness to on-manifold attacks. However, since no out-of-manifold perturbations are realized, the defense can be broken by Lp adversarial attacks. We further propose Dual Manifold Adversarial Training (DMAT) where adversarial perturbations in both latent and image spaces are used in robustifying the model. Our DMAT improves performance on normal images, and achieves comparable robustness to the standard adversarial training against Lp attacks. In addition, we observe that models defended by DMAT achieve improved robustness against novel attacks which manipulate images by global color shifts or various types of image filtering. Interestingly, similar improvements are also achieved when the defended models are tested on (out-of-manifold) natural images. These results demonstrate the potential benefits of using manifold information in enhancing robustness of deep learning models against various types of novel adversarial attacks.

PDF Details

AAAI Conference 2020 Conference Paper

Maximum Likelihood Embedding of Logistic Random Dot Product Graphs

  • Luke J. O'Connor
  • Muriel Medard
  • Soheil Feizi

A latent space model for a family of random graphs assigns real-valued vectors to nodes of the graph such that edge probabilities are determined by latent positions. Latent space models provide a natural statistical framework for graph visualizing and clustering. A latent space model of particular interest is the Random Dot Product Graph (RDPG), which can be fit using an efficient spectral method; however, this method is based on a heuristic that can fail, even in simple cases. Here, we consider a closely related latent space model, the Logistic RDPG, which uses a logistic link function to map from latent positions to edge likelihoods. Over this model, we show that asymptotically exact maximum likelihood inference of latent position vectors can be achieved using an ef- ficient spectral method. Our method involves computing top eigenvectors of a normalized adjacency matrix and scaling eigenvectors using a regression step. The novel regression scaling step is an essential part of the proposed method. In simulations, we show that our proposed method is more accurate and more robust than common practices. We also show the effectiveness of our approach over standard real networks of the karate club and political blogs.

PDF Details

ICML Conference 2020 Conference Paper

On Second-Order Group Influence Functions for Black-Box Predictions

  • Samyadeep Basu
  • Xuchen You
  • Soheil Feizi

With the rapid adoption of machine learning systems in sensitive applications, there is an increasing need to make black-box models explainable. Often we want to identify an influential group of training samples in a particular test prediction for a given machine learning model. Existing influence functions tackle this problem by using first-order approximations of the effect of removing a sample from the training set on model parameters. To compute the influence of a group of training samples (rather than an individual point) in model predictions, the change in optimal model parameters after removing that group from the training set can be large. Thus, in such cases, the first-order approximation can be loose. In this paper, we address this issue and propose second-order influence functions for identifying influential groups in test-time predictions. For linear models, across different sizes and types of groups, we show that using the proposed second-order influence function improves the correlation between the computed influence values and the ground truth ones. We also show that second-order influence functions could be used with optimization techniques to improve the selection of the most influential group for a test-sample.

Details

NeurIPS Conference 2020 Conference Paper

Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation

  • Yogesh Balaji
  • Rama Chellappa
  • Soheil Feizi

Optimal Transport (OT) distances such as Wasserstein have been used in several areas such as GANs and domain adaptation. OT, however, is very sensitive to outliers (samples with large noise) in the data since in its objective function, every sample, including outliers, is weighed similarly due to the marginal constraints. To remedy this issue, robust formulations of OT with unbalanced marginal constraints have previously been proposed. However, employing these methods in deep learning problems such as GANs and domain adaptation is challenging due to the instability of their dual optimization solvers. In this paper, we resolve these issues by deriving a computationally-efficient dual form of the robust OT optimization that is amenable to modern deep learning applications. We demonstrate the effectiveness of our formulation in two applications of GANs and domain adaptation. Our approach can train state-of-the-art GAN models on noisy datasets corrupted with outlier distributions. In particular, the proposed optimization method computes weights for training samples reflecting how difficult it is for those samples to be generated in the model. In domain adaptation, our robust OT formulation leads to improved accuracy compared to the standard adversarial adaptation methods. Our code is available at https: //github. com/yogeshbalaji/robustOT.

PDF Details

AAAI Conference 2020 Conference Paper

Robustness Certificates for Sparse Adversarial Attacks by Randomized Ablation

  • Alexander Levine
  • Soheil Feizi

Recently, techniques have been developed to provably guarantee the robustness of a classifier to adversarial perturbations of bounded L1 and L2 magnitudes by using randomized smoothing: the robust classification is a consensus of base classifications on randomly noised samples where the noise is additive. In this paper, we extend this technique to the L0 threat model. We propose an efficient and certifiably robust defense against sparse adversarial attacks by randomly ablating input features, rather than using additive noise. Experimentally, on MNIST, we can certify the classifications of over 50% of images to be robust to any distortion of at most 8 pixels. This is comparable to the observed empirical robustness of unprotected classifiers on MNIST to modern L0 attacks, demonstrating the tightness of the proposed robustness certificate. We also evaluate our certificate on ImageNet and CIFAR-10. Our certificates represent an improvement on those provided in a concurrent work (Lee et al. 2019) which uses random noise rather than ablation (median certificates of 8 pixels versus 4 pixels on MNIST; 16 pixels versus 1 pixel on ImageNet.) Additionally, we empirically demonstrate that our classifier is highly robust to modern sparse adversarial attacks on MNIST. Our classifications are robust, in median, to adversarial perturbations of up to 31 pixels, compared to 22 pixels reported as the state-of-the-art defense, at the cost of a slight decrease (around 2. 3%) in the classification accuracy. Code and supplementary material is available at https: //github. com/alevine0/randomizedAblation/.

PDF Details

ICML Conference 2020 Conference Paper

Second-Order Provable Defenses against Adversarial Attacks

  • Sahil Singla 0002
  • Soheil Feizi

A robustness certificate against adversarial examples is the minimum distance of a given input to the decision boundary of the classifier (or its lower bound). For \emph{any} perturbation of the input with a magnitude smaller than the certificate value, the classification output will provably remain unchanged. Computing exact robustness certificates for neural networks is difficult in general since it requires solving a non-convex optimization. In this paper, we provide computationally-efficient robustness certificates for neural networks with differentiable activation functions in two steps. First, we show that if the eigenvalues of the Hessian of the network (curvatures of the network) are bounded (globally or locally), we can compute a robustness certificate in the $l_2$ norm efficiently using convex optimization. Second, we derive a computationally-efficient differentiable upper bound on the curvature of a deep network. We also use the curvature bound as a regularization term during the training of the network to boost its certified robustness. Putting these results together leads to our proposed {\bf C}urvature-based {\bf R}obustness {\bf C}ertificate (CRC) and {\bf C}urvature-based {\bf R}obust {\bf T}raining (CRT). Our numerical results show that CRT leads to significantly higher certified robust accuracy compared to interval-bound propagation based training.

Details

ICML Conference 2019 Conference Paper

Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs

  • Yogesh Balaji
  • Seyed Hamed Hassani
  • Rama Chellappa
  • Soheil Feizi

Building on the success of deep learning, two modern approaches to learn a probability model from the data are Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs). VAEs consider an explicit probability model for the data and compute a generative distribution by maximizing a variational lower-bound on the log-likelihood function. GANs, however, compute a generative model by minimizing a distance between observed and generated probability distributions without considering an explicit model for the observed data. The lack of having explicit probability models in GANs prohibits computation of sample likelihoods in their frameworks and limits their use in statistical inference problems. In this work, we resolve this issue by constructing an explicit probability model that can be used to compute sample likelihood statistics in GANs. In particular, we prove that under this probability model, a family of Wasserstein GANs with an entropy regularization can be viewed as a generative model that maximizes a variational lower-bound on average sample log likelihoods, an approach that VAEs are based on. This result makes a principled connection between two modern generative models, namely GANs and VAEs. In addition to the aforementioned theoretical results, we compute likelihood statistics for GANs trained on Gaussian, MNIST, SVHN, CIFAR-10 and LSUN datasets. Our numerical results validate the proposed theory.

Details

NeurIPS Conference 2019 Conference Paper

Functional Adversarial Attacks

  • Cassidy Laidlaw
  • Soheil Feizi

We propose functional adversarial attacks, a novel class of threat models for crafting adversarial examples to fool machine learning models. Unlike a standard lp-ball threat model, a functional adversarial threat model allows only a single function to be used to perturb input features to produce an adversarial example. For example, a functional adversarial attack applied on colors of an image can change all red pixels simultaneously to light red. Such global uniform changes in images can be less perceptible than perturbing pixels of the image individually. For simplicity, we refer to functional adversarial attacks on image colors as ReColorAdv, which is the main focus of our experiments. We show that functional threat models can be combined with existing additive (lp) threat models to generate stronger threat models that allow both small, individual perturbations and large, uniform changes to an input. Moreover, we prove that such combinations encompass perturbations that would not be allowed in either constituent threat model. In practice, ReColorAdv can significantly reduce the accuracy of a ResNet-32 trained on CIFAR-10. Furthermore, to the best of our knowledge, combining ReColorAdv with other attacks leads to the strongest existing attack even after adversarial training.

PDF Details

NeurIPS Conference 2019 Conference Paper

Input-Cell Attention Reduces Vanishing Saliency of Recurrent Neural Networks

  • Aya Abdelsalam Ismail
  • Mohamed Gunady
  • Luiz Pessoa
  • Hector Corrada Bravo
  • Soheil Feizi

Recent efforts to improve the interpretability of deep neural networks use saliency to characterize the importance of input features to predictions made by models. Work on interpretability using saliency-based methods on Recurrent Neural Networks (RNNs) has mostly targeted language tasks, and their applicability to time series data is less understood. In this work we analyze saliency-based methods for RNNs, both classical and gated cell architectures. We show that RNN saliency vanishes over time, biasing detection of salient features only to later time steps and are, therefore, incapable of reliably detecting important features at arbitrary time intervals. To address this vanishing saliency problem, we propose a novel RNN cell structure (input-cell attention), which can extend any RNN cell architecture. At each time step, instead of only looking at the current input vector, input-cell attention uses a fixed-size matrix embedding, each row of the matrix attending to different inputs from current or previous time steps. Using synthetic data, we show that the saliency map produced by the input-cell attention RNN is able to faithfully detect important features regardless of their occurrence in time. We also apply the input-cell attention RNN on a neuroscience task analyzing functional Magnetic Resonance Imaging (fMRI) data for human subjects performing a variety of tasks. In this case, we use saliency to characterize brain regions (input features) for which activity is important to distinguish between tasks. We show that standard RNN architectures are only capable of detecting important brain regions in the last few time steps of the fMRI data, while the input-cell attention model is able to detect important brain region activity across time without latter time step biases.

PDF Details

NeurIPS Conference 2019 Conference Paper

Quantum Wasserstein Generative Adversarial Networks

  • Shouvanik Chakrabarti
  • Huang Yiming
  • Tongyang Li
  • Soheil Feizi
  • Xiaodi Wu

The study of quantum generative models is well-motivated, not only because of its importance in quantum machine learning and quantum chemistry but also because of the perspective of its implementation on near-term quantum machines. Inspired by previous studies on the adversarial training of classical and quantum generative models, we propose the first design of quantum Wasserstein Generative Adversarial Networks (WGANs), which has been shown to improve the robustness and the scalability of the adversarial training of quantum generative models even on noisy quantum hardware. Specifically, we propose a definition of the Wasserstein semimetric between quantum data, which inherits a few key theoretical merits of its classical counterpart. We also demonstrate how to turn the quantum Wasserstein semimetric into a concrete design of quantum WGANs that can be efficiently implemented on quantum machines. Our numerical study, via classical simulation of quantum systems, shows the more robust and scalable numerical performance of our quantum WGANs over other quantum GAN proposals. As a surprising application, our quantum WGAN has been used to generate a 3-qubit quantum circuit of ~50 gates that well approximates a 3-qubit 1-d Hamiltonian simulation circuit that requires over 10k gates using standard techniques.

PDF Details

ICML Conference 2019 Conference Paper

Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation

  • Sahil Singla 0002
  • Eric Wallace
  • Shi Feng 0005
  • Soheil Feizi

Current saliency map interpretations for neural networks generally rely on two key assumptions. First, they use first-order approximations of the loss function, neglecting higher-order terms such as the loss curvature. Second, they evaluate each feature’s importance in isolation, ignoring feature interdependencies. This work studies the effect of relaxing these two assumptions. First, we characterize a closed-form formula for the input Hessian matrix of a deep ReLU network. Using this formula, we show that, for classification problems with many classes, if a prediction has high probability then including the Hessian term has a small impact on the interpretation. We prove this result by demonstrating that these conditions cause the Hessian matrix to be approximately rank one and its leading eigenvector to be almost parallel to the gradient of the loss. We empirically validate this theory by interpreting ImageNet classifiers. Second, we incorporate feature interdependencies by calculating the importance of group-features using a sparsity regularization term. We use an L0 - L1 relaxation technique along with proximal gradient descent to efficiently compute group-feature importance values. Our empirical results show that our method significantly improves deep learning interpretations.

Details

NeurIPS Conference 2018 Conference Paper

Porcupine Neural Networks: Approximating Neural Network Landscapes

  • Soheil Feizi
  • Hamid Javadi
  • Jesse Zhang
  • David Tse

Neural networks have been used prominently in several machine learning and statistics applications. In general, the underlying optimization of neural networks is non-convex which makes analyzing their performance challenging. In this paper, we take another approach to this problem by constraining the network such that the corresponding optimization landscape has good theoretical properties without significantly compromising performance. In particular, for two-layer neural networks we introduce Porcupine Neural Networks (PNNs) whose weight vectors are constrained to lie over a finite set of lines. We show that most local optima of PNN optimizations are global while we have a characterization of regions where bad local optimizers may exist. Moreover, our theoretical and empirical results suggest that an unconstrained neural network can be approximated using a polynomially-large PNN.

PDF Details

NeurIPS Conference 2017 Conference Paper

Tensor Biclustering

  • Soheil Feizi
  • Hamid Javadi
  • David Tse

Consider a dataset where data is collected on multiple features of multiple individuals over multiple times. This type of data can be represented as a three dimensional individual/feature/time tensor and has become increasingly prominent in various areas of science. The tensor biclustering problem computes a subset of individuals and a subset of features whose signal trajectories over time lie in a low-dimensional subspace, modeling similarity among the signal trajectories while allowing different scalings across different individuals or different features. We study the information-theoretic limit of this problem under a generative model. Moreover, we propose an efficient spectral algorithm to solve the tensor biclustering problem and analyze its achievability bound in an asymptotic regime. Finally, we show the efficiency of our proposed method in several synthetic and real datasets.

PDF Details

NeurIPS Conference 2014 Conference Paper

Biclustering Using Message Passing

  • Luke O'Connor
  • Soheil Feizi

Biclustering is the analog of clustering on a bipartite graph. Existent methods infer biclusters through local search strategies that find one cluster at a time; a common technique is to update the row memberships based on the current column memberships, and vice versa. We propose a biclustering algorithm that maximizes a global objective function using message passing. Our objective function closely approximates a general likelihood function, separating a cluster size penalty term into row- and column-count penalties. Because we use a global optimization framework, our approach excels at resolving the overlaps between biclusters, which are important features of biclusters in practice. Moreover, Expectation-Maximization can be used to learn the model parameters if they are unknown. In simulations, we find that our method outperforms two of the best existing biclustering algorithms, ISA and LAS, when the planted clusters overlap. Applied to three gene expression datasets, our method finds coregulated gene clusters that have high quality in terms of cluster size and density.

PDF Details
v2026.09.13