Author name cluster

Nicolas Papernot

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.

50 papers

2 author rows

ICLR Conference 2025 Conference Paper

Breach By A Thousand Leaks: Unsafe Information Leakage in 'Safe' AI Responses

David Glukhov
Ziwen Han
Ilia Shumailov
Vardan Papyan
Nicolas Papernot

Vulnerability of Frontier language models to misuse has prompted the development of safety measures like filters and alignment training seeking to ensure safety through robustness to adversarially crafted prompts. We assert that robustness is fundamentally insufficient for ensuring safety goals due to inferential threats from dual-intent queries, with current defenses and evaluations failing to account for these risks. To quantify these risks, we introduce a new safety evaluation framework based on $\textit{impermissible information leakage}$ of model outputs and demonstrate how our proposed question-decomposition attack can extract dangerous knowledge from a censored LLM more effectively than traditional jailbreaking. Underlying our proposed evaluation method is a novel information-theoretic threat model of $\textit{inferential adversaries}$, distinguished from $\textit{security adversaries}$, such as jailbreaks, in that success involves inferring impermissible knowledge from victim outputs as opposed to forcing explicitly impermissible victim outputs. Through our information-theoretic framework, we show that ensuring safety against inferential adversaries requires defenses which bound impermissible information leakage, and, such defenses inevitably incur safety-utility trade-offs.

ICML Conference 2025 Conference Paper

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention

Stephan Rabanser
Ali Shahin Shamsabadi
Olive Franzese
Xiao Wang 0012
Adrian Weller
Nicolas Papernot

Cautious predictions—where a machine learning model abstains when uncertain—are crucial for limiting harmful errors in safety-critical applications. In this work, we identify a novel threat: a dishonest institution can exploit these mechanisms to discriminate or unjustly deny services under the guise of uncertainty. We demonstrate the practicality of this threat by introducing an uncertainty-inducing attack called Mirage, which deliberately reduces confidence in targeted input regions, thereby covertly disadvantaging specific individuals. At the same time, Mirage maintains high predictive performance across all data points. To counter this threat, we propose Confidential Guardian, a framework that analyzes calibration metrics on a reference dataset to detect artificially suppressed confidence. Additionally, it employs zero-knowledge proofs of verified inference to ensure that reported confidence scores genuinely originate from the deployed model. This prevents the provider from fabricating arbitrary model confidence values while protecting the model’s proprietary details. Our results confirm that Confidential Guardian effectively prevents the misuse of cautious predictions, providing verifiable assurances that abstention reflects genuine model uncertainty rather than malicious intent.

ICML Conference 2025 Conference Paper

Fast Exact Unlearning for In-Context Learning Data for LLMs

Andrei Ioan Muresanu
Anvith Thudi
Michael R. Zhang
Nicolas Papernot

Modern machine learning models are expensive to train, and there is a growing concern about the challenge of retroactively removing specific training data. Achieving exact unlearning in deep learning pipelines—producing models as if certain data had never been included in training—remains an open problem. In this paper, we revisit exact unlearning in deep learning and show that for large language models (LLMs) we can efficiently exactly unlearn “fine-tuning data" (the data used to adapt a pre-trained model). This follows from two observations. First, we can use in-context learning to adapt the LLM to the fine-tuning dataset instead of SGD based algorithms. Second, we show that accurate in-context learning can be done with quantized k-means, which allows for effectively constant time unlearning operations. Our evaluation shows that this unlearning recipe has similar performance to fine-tuning alternatives, but vastly reduces the unlearning costs. Our study also highlights the need for new measures of unlearning cost when adapting the learning algorithm to have faster unlearn operations.

ICML Conference 2025 Conference Paper

Language Models May Verbatim Complete Text They Were Not Explicitly Trained On

Ken Liu
Christopher A. Choquette-Choo
Matthew Jagielski
Peter Kairouz
Sanmi Koyejo
Percy Liang
Nicolas Papernot

An important question today is whether a given text was used to train a large language model (LLM). A completion test is often employed: check if the LLM completes a sufficiently complex text. This, however, requires a ground-truth definition of membership; most commonly, it is defined as a member based on the n-gram overlap between the target text and any text in the dataset. In this work, we demonstrate that this n-gram based membership definition can be effectively gamed. We study scenarios where sequences are non-members for a given n and we find that completion tests still succeed. We find many natural cases of this phenomenon by retraining LLMs from scratch after removing all training samples that were completed; these cases include exact duplicates, near-duplicates, and even short overlaps. They showcase that it is difficult to find a single viable choice of n for membership definitions. Using these insights, we design adversarial datasets that can cause a given target sequence to be completed without containing it, for any reasonable choice of n. Our findings highlight the inadequacy of n-gram membership, suggesting membership definitions fail to account for auxiliary information available to the training algorithm.

TMLR Journal 2025 Journal Article

Learned-Database Systems Security

Roei Schuster
Jin Peng Zhou
Thorsten Eisenhofer
Paul Grubbs
Nicolas Papernot

A learned database system uses machine learning (ML) internally to improve performance. We can expect such systems to be vulnerable to some adversarial-ML attacks. Often, the learned component is shared between mutually-distrusting users or processes, much like microarchitectural resources such as caches, potentially giving rise to highly-realistic attacker models. However, compared to attacks on other ML-based systems, attackers face a level of indirection as they cannot interact directly with the learned model. Additionally, the difference between the attack surface of learned and non-learned versions of the same system is often subtle. These factors obfuscate the de-facto risks that the incorporation of ML carries. We analyze the root causes of potentially-increased attack surface in learned database systems and develop a framework for identifying vulnerabilities that stem from the use of ML. We apply our framework to a broad set of learned components currently being explored in the database community. To empirically validate the vulnerabilities surfaced by our framework, we choose 3 of them and implement and evaluate exploits against these. We show that the use of ML cause leakage of past queries in a database, enable a poisoning attack that causes exponential memory blowup in an index structure and crashes it in seconds, and enable index users to snoop on each others' key distributions by timing queries over their own keys. We find that adversarial ML is an universal threat against learned components in database systems, point to open research gaps in our understanding of learned-systems security, and conclude by discussing mitigations, while noting that data leakage is inherent in systems whose learned component is shared between multiple parties.

ICML Conference 2025 Conference Paper

Leveraging Per-Instance Privacy for Machine Unlearning

Nazanin Mohammadi Sepahvand
Anvith Thudi
Berivan Isik
Ashmita Bhattacharyya
Nicolas Papernot
Eleni Triantafillou
Daniel M. Roy 0001
Gintare Karolina Dziugaite

We present a principled, per-instance approach to quantifying the difficulty of unlearning via fine-tuning. We begin by sharpening an analysis of noisy gradient descent for unlearning (Chien et al. , 2024), obtaining a better utility–unlearning trade-off by replacing worst-case privacy loss bounds with per-instance privacy losses (Thudi et al. , 2024), each of which bounds the (R ényi) divergence to retraining without an individual datapoint. To demonstrate the practical applicability of our theory, we present empirical results showing that our theoretical predictions are born out both for Stochastic Gradient Langevin Dynamics (SGLD) as well as for standard fine-tuning without explicit noise. We further demonstrate that per-instance privacy losses correlate well with several existing data difficulty metrics, while also identifying harder groups of data points, and introduce novel evaluation methods based on loss barriers. All together, our findings provide a foundation for more efficient and adaptive unlearning strategies tailored to the unique properties of individual data points.

NeurIPS Conference 2025 Conference Paper

Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research

A. Feder Cooper
Christopher A. Choquette-Choo
Miranda Bogen
Kevin Klyman
Matthew Jagielski
Katja Filippova
Ken Liu
Alex Chouldechova

"Machine unlearning" is a popular proposed solution for mitigating the existence of content in an AI model that is problematic for legal or moral reasons, including privacy, copyright, safety, and more. For example, unlearning is often invoked as a solution for removing the effects of specific information from a generative-AI model's parameters, e. g. , a particular individual's personal data or the inclusion of copyrighted content in the model's training data. Unlearning is also proposed as a way to prevent a model from generating targeted types of information in its outputs, e. g. , generations that closely resemble a particular individual's data or reflect the concept of "Spiderman. " Both of these goals--the targeted removal of information from a model and the targeted suppression of information from a model's outputs--present various technical and substantive challenges. We provide a framework for ML researchers and policymakers to think rigorously about these challenges, identifying several mismatches between the goals of unlearning and feasible implementations. These mismatches explain why unlearning is not a general-purpose solution for circumscribing generative-AI model behavior in service of broader positive impact.

TMLR Journal 2025 Journal Article

Selective Prediction via Training Dynamics

Stephan Rabanser
Anvith Thudi
Kimia Hamidieh
Adam Dziedzic
Israfil Bahceci
Akram Bin Sediq
HAMZA SOKUN
Nicolas Papernot

Selective Prediction is the task of rejecting inputs a model would predict incorrectly on. This involves a trade-off between input space coverage (how many data points are accepted) and model utility (how good is the performance on accepted data points). Current methods for selective prediction typically impose constraints on either the model architecture or the optimization objective; this inhibits their usage in practice and introduces unknown interactions with pre-existing loss functions. In contrast to prior work, we show that state-of-the-art se- lective prediction performance can be attained solely from studying the (discretized) training dynamics of a model. We propose a general framework that, given a test input, monitors metrics capturing the instability of predictions from intermediate models (i.e., checkpoints) obtained during training w.r.t. the final model’s prediction. In particular, we reject data points exhibiting too much disagreement with the final prediction at late stages in training. The proposed rejection mechanism is domain-agnostic (i.e., it works for both discrete and real-valued prediction) and can be flexibly combined with existing selective prediction approaches as it does not require any train-time modifications. Our experimental evaluation on image classification, regression, and time series problems shows that our method beats past state-of-the-art accuracy/utility trade-offs on typical selective prediction benchmarks.

ICML Conference 2025 Conference Paper

Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings

Angéline Pouget
Mohammad Yaghini
Stephan Rabanser
Nicolas Papernot

Deploying machine learning models in safety-critical domains poses a key challenge: ensuring reliable model performance on downstream user data without access to ground truth labels for direct validation. We propose the suitability filter, a novel framework designed to detect performance deterioration by utilizing suitability signals —model output features that are sensitive to covariate shifts and indicative of potential prediction errors. The suitability filter evaluates whether classifier accuracy on unlabeled user data shows significant degradation compared to the accuracy measured on the labeled test dataset. Specifically, it ensures that this degradation does not exceed a pre-specified margin, which represents the maximum acceptable drop in accuracy. To achieve reliable performance evaluation, we aggregate suitability signals for both test and user data and compare these empirical distributions using statistical hypothesis testing, thus providing insights into decision uncertainty. Our modular method adapts to various models and domains. Empirical evaluations across different classification tasks demonstrate that the suitability filter reliably detects performance deviations due to covariate shift. This enables proactive mitigation of potential failures in high-stakes applications.

ICLR Conference 2025 Conference Paper

Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model

Tudor Ioan Cebere
Aurélien Bellet
Nicolas Papernot

Machine learning models can be trained with formal privacy guarantees via differentially private optimizers such as DP-SGD. In this work, we focus on a threat model where the adversary has access only to the final model, with no visibility into intermediate updates. In the literature, this ``hidden state'' threat model exhibits a significant gap between the lower bound from empirical privacy auditing and the theoretical upper bound provided by privacy accounting. To challenge this gap, we propose to audit this threat model with adversaries that craft a gradient sequence designed to maximize the privacy loss of the final model without relying on intermediate updates. Our experiments show that this approach consistently outperforms previous attempts at auditing the hidden state model. Furthermore, our results advance the understanding of achievable privacy guarantees within this threat model. Specifically, when the crafted gradient is inserted at every optimization step, we show that concealing the intermediate model updates in DP-SGD does not enhance the privacy guarantees. The situation is more complex when the crafted gradient is not inserted at every step: our auditing lower bound matches the privacy upper bound only for an adversarially-chosen loss landscape and a sufficiently large batch size. This suggests that existing privacy upper bounds can be improved in certain regimes.

NeurIPS Conference 2025 Conference Paper

What Does It Take to Build a Performant Selective Classifier?

Stephan Rabanser
Nicolas Papernot

Selective classifiers improve model reliability by abstaining on inputs the model deems uncertain. However, few practical approaches achieve the gold-standard performance of a perfect-ordering oracle that accepts examples exactly in order of correctness. Our work formalizes this shortfall as the selective-classification gap and present the first finite-sample decomposition of this gap to five distinct sources of looseness: Bayes noise, approximation error, ranking error, statistical noise, and implementation- or shift-induced slack. Our analysis reveals that monotone post-hoc calibration—often believed to strengthen selective classifiers—has limited impact on closing this gap, since it rarely alters the model’s underlying score ranking. Bridging the gap therefore requires scoring mechanisms that can effectively reorder predictions rather than merely rescale them. We validate our decomposition on synthetic two-moons data and on real-world vision and language benchmarks, isolating each error component through controlled experiments. Our results show that (i) Bayes noise and limited model capacity can account for substantial gaps, (ii) only non-monotone or feature-aware calibrators consistently reduce the ranking term, and (iii) distribution shift introduces a separate slack that demands distributionally robust training. Together, our decomposition yields a quantitative error budget as well as actionable design guidelines that practitioners can use to build selective classifiers which approximate ideal oracle behavior more closely.

ICML Conference 2024 Conference Paper

Auditing Private Prediction

Karan Chadha
Matthew Jagielski
Nicolas Papernot
Christopher A. Choquette-Choo
Milad Nasr

Differential privacy (DP) offers a theoretical upper bound on the potential privacy leakage of an algorithm, while empirical auditing establishes a practical lower bound. Auditing techniques exist for DP training algorithms. However machine learning can also be made private at inference. We propose the first framework for auditing private prediction where we instantiate adversaries with varying poisoning and query capabilities. This enables us to study the privacy leakage of four private prediction algorithms: PATE (Papernot et al. , 2016), CaPC (Choquette-Choo et al. , 2020), PromptPATE (Duan et al. , 2023), and Private-kNN (Zhu et al. , 2020). To conduct our audit, we introduce novel techniques to empirically evaluate privacy leakage in terms of Renyi DP. Our experiments show that (i) the privacy analysis of private prediction can be improved, (ii) algorithms which are easier to poison lead to much higher privacy leakage, and (iii) the privacy leakage is significantly lower for adversaries without query control than those with full control.

TMLR Journal 2024 Journal Article

Augment then Smooth: Reconciling Differential Privacy with Certified Robustness

Jiapeng Wu
Atiyeh Ashari Ghomi
David Glukhov
Jesse C. Cresswell
Franziska Boenisch
Nicolas Papernot

Machine learning models are susceptible to a variety of attacks that can erode trust, including attacks against the privacy of training data, and adversarial examples that jeopardize model accuracy. Differential privacy and certified robustness are effective frameworks for combating these two threats respectively, as they each provide future-proof guarantees. However, we show that standard differentially private model training is insufficient for providing strong certified robustness guarantees. Indeed, combining differential privacy and certified robustness in a single system is non-trivial, leading previous works to introduce complex training schemes that lack flexibility. In this work, we present DP-CERT, a simple and effective method that achieves both privacy and robustness guarantees simultaneously by integrating randomized smoothing into standard differentially private model training. Compared to the leading prior work, DP-CERT gives up to a 2.5x increase in certified accuracy for the same differential privacy guarantee on CIFAR10. Through in-depth per-sample metric analysis, we find that larger certifiable radii correlate with smaller local Lipschitz constants, and show that DP-CERT effectively reduces Lipschitz constants compared to other differentially private training methods. Code is available at github.com/layer6ai-labs/dp-cert.

TMLR Journal 2024 Journal Article

Beyond Labeling Oracles - What does it mean to steal ML models?

Avital Shafran
Ilia Shumailov
Murat A Erdogdu
Nicolas Papernot

Model extraction attacks are designed to steal trained models with only query access, as is often provided through APIs that ML-as-a-Service providers offer. Machine Learning (ML) models are expensive to train, in part because data is hard to obtain, and a primary incentive for model extraction is to acquire a model while incurring less cost than training from scratch. Literature on model extraction commonly claims or presumes that the attacker is able to save on both data acquisition and labeling costs. We thoroughly evaluate this assumption and find that the attacker often does not. This is because current attacks implicitly rely on the adversary being able to sample from the victim model's data distribution. We thoroughly research factors influencing the success of model extraction. We discover that prior knowledge of the attacker, i.e., access to in-distribution data, dominates other factors like the attack policy the adversary follows to choose which queries to make to the victim model API. Our findings urge the community to redefine the adversarial goals of ME attacks as current evaluation methods misinterpret the ME performance.

ICLR Conference 2024 Conference Paper

Confidential-DPproof: Confidential Proof of Differentially Private Training

Ali Shahin Shamsabadi
Gefei Tan
Tudor Ioan Cebere
Aurélien Bellet
Hamed Haddadi 0001
Nicolas Papernot
Xiao Wang 0012
Adrian Weller

Post hoc privacy auditing techniques can be used to test the privacy guarantees of a model, but come with several limitations: (i) they can only establish lower bounds on the privacy loss, (ii) the intermediate model updates and some data must be shared with the auditor to get a better approximation of the privacy loss, and (iii) the auditor typically faces a steep computational cost to run a large number of attacks. In this paper, we propose to proactively generate a cryptographic certificate of privacy during training to forego such auditing limitations. We introduce Confidential-DPproof , a framework for Confidential Proof of Differentially Private Training, which enhances training with a certificate of the $(\varepsilon,\delta)$-DP guarantee achieved. To obtain this certificate without revealing information about the training data or model, we design a customized zero-knowledge proof protocol tailored to the requirements introduced by differentially private training, including random noise addition and privacy amplification by subsampling. In experiments on CIFAR-10, Confidential-DPproof trains a model achieving state-of-the-art $91$% test accuracy with a certified privacy guarantee of $(\varepsilon=0.55,\delta=10^{-5})$-DP in approximately 100 hours.

TMLR Journal 2024 Journal Article

From Differential Privacy to Bounds on Membership Inference: Less can be More

Anvith Thudi
Ilia Shumailov
Franziska Boenisch
Nicolas Papernot

Differential Privacy (DP) is the de facto standard for reasoning about the privacy of a training algorithm. Yet, learning with DP often yields poor performance unless one trains on a large dataset. In this paper, we instead outline how training on less data can be beneficial when we are only interested in defending against specific attacks; we take the canonical example of defending against membership inference. To arrive at this result, we first derive (tight) bounds on the success of all membership inference attacks. These bounds do not replace DP, rather they introduce a complementary interpretation of a DP algorithm's ability to defend against membership inference specifically. Because our bound more tightly captures the effect of how training data was selected, we can show that decreasing the sampling rate when constructing the training dataset has a disparate effect on the bound when compared to strengthening the DP guarantee. Thus, when the privacy protection we care about is defending against membership inference, training on less data can yield more advantageous trade-offs between preventing membership inference and utility than strengthening the DP guarantee. We empirically illustrate this on MNIST, CIFAR10 and SVHN-extended.

NeurIPS Conference 2024 Conference Paper

LLM Dataset Inference: Did you train on my dataset?

Pratyush Maini
Hengrui Jia
Nicolas Papernot
Adam Dziedzic

The proliferation of large language models (LLMs) in the real world has come with a rise in copyright cases against companies for training their models on unlicensed data from the internet. Recent works have presented methods to identify if individual text sequences were members of the model's training data, known as membership inference attacks (MIAs). We demonstrate that the apparent success of these MIAs is confounded by selecting non-members (text sequences not used for training) belonging to a different distribution from the members (e. g. , temporally shifted recent Wikipedia articles compared with ones used to train the model). This distribution shift makes membership inference appear successful. However, most MIA methods perform no better than random guessing when discriminating between members and non-members from the same distribution (e. g. , in this case, the same period of time). Even when MIAs work, we find that different MIAs succeed at inferring membership of samples from different distributions. Instead, we propose a new dataset inference method to accurately identify the datasets used to train large language models. This paradigm sits realistically in the modern-day copyright landscape, where authors claim that an LLM is trained over multiple documents (such as a book) written by them, rather than one particular paragraph. While dataset inference shares many of the challenges of membership inference, we solve it by selectively combining the MIAs that provide positive signal for a given distribution, and aggregating them to perform a statistical test on a given dataset. Our approach successfully distinguishes the train and test sets of different subsets of the Pile with statistically significant p-values $< 0. 1$, without any false positives.

PDF Details DOI

ICLR Conference 2024 Conference Paper

Memorization in Self-Supervised Learning Improves Downstream Generalization

Wenhao Wang
Muhammad Ahmad Kaleem
Adam Dziedzic
Michael Backes 0001
Nicolas Papernot
Franziska Boenisch

Self-supervised learning (SSL) has recently received significant attention due to its ability to train high-performance encoders purely on unlabeled data---often scraped from the internet. This data can still be sensitive and empirical evidence suggests that SSL encoders memorize private information of their training data and can disclose them at inference time. Since existing theoretical definitions of memorization from supervised learning rely on labels, they do not transfer to SSL. To address this gap, we propose a framework for defining memorization within the context of SSL. Our definition compares the difference in alignment of representations for data points and their augmented views returned by both encoders that were trained on these data points and encoders that were not. Through comprehensive empirical analysis on diverse encoder architectures and datasets we highlight that even though SSL relies on large datasets and strong augmentations---both known in supervised learning as regularization techniques that reduce overfitting---still significant fractions of training data points experience high memorization. Through our empirical results, we show that this memorization is essential for encoders to achieve higher generalization performance on different downstream tasks.

ICML Conference 2024 Conference Paper

Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches

David Glukhov
Ilia Shumailov
Yarin Gal
Nicolas Papernot
Vardan Papyan

Large language models (LLMs) have exhibited impressive capabilities in comprehending complex instructions. However, their blind adherence to provided instructions has led to concerns regarding risks of malicious use. Existing defence mechanisms, such as model fine-tuning or output censorship methods have proven to be fallible at ensuring that LLMs do not return semantically impermissible responses. We present fundamental limitations of verifying the semantic properties of LLM outputs and identifying compositional threats, illustrating inherent challenges of current approaches to censoring LLM outputs. Specifically, we demonstrate that semantic censorship can be perceived as an undecidable problem, and semantic properties of LLM outputs can become impossible to verify when the LLM is capable of providing "encrypted" outputs. We further show challenges of censorship can extend beyond just semantic censorship, as attackers can reconstruct impermissible outputs from a collection of permissible ones. Consequently, we call for a re-evaluation of the problem of censorship and its goals, stressing the need for new definitions and approaches to censorship. In addition, we provide an initial attempt toward achieving this goal through syntactic censorship, drawing from a security perspective to design censorship methods that can provide guarantees.

NeurIPS Conference 2024 Conference Paper

Temporal-Difference Learning Using Distributed Error Signals

Jonas Guan
Shon E. Verch
Claas Voelcker
Ethan C. Jackson
Nicolas Papernot
William A. Cunningham

A computational problem in biological reward-based learning is how credit assignment is performed in the nucleus accumbens (NAc). Much research suggests that NAc dopamine encodes temporal-difference (TD) errors for learning value predictions. However, dopamine is synchronously distributed in regionally homogeneous concentrations, which does not support explicit credit assignment (like used by backpropagation). It is unclear whether distributed errors alone are sufficient for synapses to make coordinated updates to learn complex, nonlinear reward-based learning tasks. We design a new deep Q-learning algorithm, Artificial Dopamine, to computationally demonstrate that synchronously distributed, per-layer TD errors may be sufficient to learn surprisingly complex RL tasks. We empirically evaluate our algorithm on MinAtar, the DeepMind Control Suite, and classic control tasks, and show it often achieves comparable performance to deep RL algorithms that use backpropagation.

PDF Details DOI

ICML Conference 2024 Conference Paper

The Fundamental Limits of Least-Privilege Learning

Theresa Stadler
Bogdan Kulynych
Michael Gastpar
Nicolas Papernot
Carmela Troncoso

The promise of least-privilege learning – to find feature representations that are useful for a learning task but prevent inference of any sensitive information unrelated to this task – is highly appealing. However, so far this concept has only been stated informally. It thus remains an open question whether and how we can achieve this goal. In this work, we provide the first formalisation of the least-privilege principle for machine learning and characterise its feasibility. We prove that there is a fundamental trade-off between a representation’s utility for a given task and its leakage beyond the intended task: it is not possible to learn representations that have high utility for the intended task but, at the same time, prevent inference of any attribute other than the task label itself. This trade-off holds regardless of the technique used to learn the feature mappings that produce these representations. We empirically validate this result for a wide range of learning techniques, model architectures, and datasets.

ICLR Conference 2023 Conference Paper

Confidential-PROFITT: Confidential PROof of FaIr Training of Trees

Ali Shahin Shamsabadi
Sierra Calanda Wyllie
Nicholas Franzese
Natalie Dullerud
Sébastien Gambs
Nicolas Papernot
Xiao Wang 0012
Adrian Weller

Post hoc auditing of model fairness suffers from potential drawbacks: (1) auditing may be highly sensitive to the test samples chosen; (2) the model and/or its training data may need to be shared with an auditor thereby breaking confidentiality. We address these issues by instead providing a certificate that demonstrates that the learning algorithm itself is fair, and hence, as a consequence, so too is the trained model. We introduce a method to provide a confidential proof of fairness for training, in the context of widely used decision trees, which we term Confidential-PROFITT. We propose novel fair decision tree learning algorithms along with customized zero-knowledge proof protocols to obtain a proof of fairness that can be audited by a third party. Using zero-knowledge proofs enables us to guarantee confidentiality of both the model and its training data. We show empirically that bounding the information gain of each node with respect to the sensitive attributes reduces the unfairness of the final tree. In extensive experiments on the COMPAS, Communities and Crime, Default Credit, and Adult datasets, we demonstrate that a company can use Confidential-PROFITT to certify the fairness of their decision tree to an auditor in less than 2 minutes, thus indicating the applicability of our approach. This is true for both the demographic parity and equalized odds definitions of fairness. Finally, we extend Confidential-PROFITT to apply to ensembles of trees.

NeurIPS Conference 2023 Conference Paper

Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models

Haonan Duan
Adam Dziedzic
Nicolas Papernot
Franziska Boenisch

Large language models (LLMs) are excellent in-context learners. However, the sensitivity of data contained in prompts raises privacy concerns. Our work first shows that these concerns are valid: we instantiate a simple but highly effective membership inference attack against the data used to prompt LLMs. To address this vulnerability, one could forego prompting and resort to fine-tuning LLMs with known algorithms for private gradient descent. However, this comes at the expense of the practicality and efficiency offered by prompting. Therefore, we propose to privately learn to prompt. We first show that soft prompts can be obtained privately through gradient descent on downstream data. However, this is not the case for discrete prompts. Thus, we orchestrate a noisy vote among an ensemble of LLMs presented with different prompts, i. e. , a flock of stochastic parrots. The vote privately transfers the flock's knowledge into a single public prompt. We show that LLMs prompted with our private algorithms closely match the non-private baselines. For example, using GPT3 as the base model, we achieve a downstream accuracy of 92. 7% on the sst2 dataset with $(\varepsilon=0. 147, \delta=10^{-6})$-differential privacy vs. 95. 2% for the non-private baseline. Through our experiments, we also show that our prompt-based approach is easily deployed with existing commercial~APIs.

NeurIPS Conference 2023 Conference Paper

Have it your way: Individualized Privacy Assignment for DP-SGD

Franziska Boenisch
Christopher Mühl
Adam Dziedzic
Roy Rinberg
Nicolas Papernot

When training a machine learning model with differential privacy, one sets a privacy budget. This uniform budget represents an overall maximal privacy violation that any user is willing to face by contributing their data to the training set. We argue that this approach is limited because different users may have different privacy expectations. Thus, setting a uniform privacy budget across all points may be overly conservative for some users or, conversely, not sufficiently protective for others. In this paper, we capture these preferences through individualized privacy budgets. To demonstrate their practicality, we introduce a variant of Differentially Private Stochastic Gradient Descent (DP-SGD) which supports such individualized budgets. DP-SGD is the canonical approach to training models with differential privacy. We modify its data sampling and gradient noising mechanisms to arrive at our approach, which we call Individualized DP-SGD (IDP-SGD). Because IDP-SGD provides privacy guarantees tailored to the preferences of individual users and their data points, we empirically find it to improve privacy-utility trade-offs.

ICLR Conference 2023 Conference Paper

Measuring Forgetting of Memorized Training Examples

Matthew Jagielski
Om Thakkar 0001
Florian Tramèr
Daphne Ippolito
Katherine Lee
Nicholas Carlini
Eric Wallace
Shuang Song 0001

Machine learning models exhibit two seemingly contradictory phenomena: training data memorization and various forms of forgetting. In memorization, models overfit specific training examples and become susceptible to privacy attacks. In forgetting, examples which appeared early in training are forgotten by the end. In this work, we connect these phenomena. We propose a technique to measure to what extent models ``forget'' the specifics of training examples, becoming less susceptible to privacy attacks on examples they have not seen recently. We show that, while non-convexity can prevent forgetting from happening in the worst-case, standard image,speech, and language models empirically do forget examples over time. We identify nondeterminism as a potential explanation, showing that deterministically trained models do not forget. Our results suggest that examples seen early when training with extremely large datasets---for instance those examples used to pre-train a model---may observe privacy benefits at the expense of examples seen later.

NeurIPS Conference 2023 Conference Paper

Robust and Actively Secure Serverless Collaborative Learning

Nicholas Franzese
Adam Dziedzic
Christopher A. Choquette-Choo
Mark R Thomas
Muhammad Ahmad Kaleem
Stephan Rabanser
Congyu Fang
Somesh Jha

Collaborative machine learning (ML) is widely used to enable institutions to learn better models from distributed data. While collaborative approaches to learning intuitively protect user data, they remain vulnerable to either the server, the clients, or both, deviating from the protocol. Indeed, because the protocol is asymmetric, a malicious server can abuse its power to reconstruct client data points. Conversely, malicious clients can corrupt learning with malicious updates. Thus, both clients and servers require a guarantee when the other cannot be trusted to fully cooperate. In this work, we propose a peer-to-peer (P2P) learning scheme that is secure against malicious servers and robust to malicious clients. Our core contribution is a generic framework that transforms any (compatible) algorithm for robust aggregation of model updates to the setting where servers and clients can act maliciously. Finally, we demonstrate the computational efficiency of our approach even with 1-million parameter models trained by 100s of peers on standard datasets.

NeurIPS Conference 2023 Conference Paper

Training Private Models That Know What They Don’t Know

Stephan Rabanser
Anvith Thudi
Abhradeep Guha Thakurta
Krishnamurthy Dvijotham
Nicolas Papernot

Training reliable deep learning models which avoid making overconfident but incorrect predictions is a longstanding challenge. This challenge is further exacerbated when learning has to be differentially private: protection provided to sensitive data comes at the price of injecting additional randomness into the learning process. In this work, we conduct a thorough empirical investigation of selective classifiers---that can abstain under uncertainty---under a differential privacy constraint. We find that some popular selective prediction approaches are ineffective in a differentially private setting because they increase the risk of privacy leakage. At the same time, we identify that a recent approach that only uses checkpoints produced by an off-the-shelf private learning algorithm stands out as particularly suitable under DP. Further, we show that differential privacy does not just harm utility but also degrades selective classification performance. To analyze this effect across privacy levels, we propose a novel evaluation mechanism which isolates selective prediction performance across model utility levels at full coverage. Our experimental results show that recovering the performance level attainable by non-private models is possible but comes at a considerable coverage cost as the privacy budget decreases.

ICLR Conference 2022 Conference Paper

A Zest of LIME: Towards Architecture-Independent Model Distances

Hengrui Jia 0001
Hongyu Chen
Jonas Guan
Ali Shahin Shamsabadi
Nicolas Papernot

Definitions of the distance between two machine learning models either characterize the similarity of the models' predictions or of their weights. While similarity of weights is attractive because it implies similarity of predictions in the limit, it suffers from being inapplicable to comparing models with different architectures. On the other hand, the similarity of predictions is broadly applicable but depends heavily on the choice of model inputs during comparison. In this paper, we instead propose to compute distance between black-box models by comparing their Local Interpretable Model-Agnostic Explanations (LIME). To compare two models, we take a reference dataset, and locally approximate the models on each reference point with linear models trained by LIME. We then compute the cosine distance between the concatenated weights of the linear models. This yields an approach that is both architecture-independent and possesses the benefits of comparing models in weight space. We empirically show that our method, which we call Zest, can be applied to two problems that require measurements of model similarity: detecting model stealing and machine unlearning.

NeurIPS Conference 2022 Conference Paper

Dataset Inference for Self-Supervised Models

Adam Dziedzic
Haonan Duan
Muhammad Ahmad Kaleem
Nikita Dhawan
Jonas Guan
Yannis Cattan
Franziska Boenisch
Nicolas Papernot

Self-supervised models are increasingly prevalent in machine learning (ML) since they reduce the need for expensively labeled data. Because of their versatility in downstream applications, they are increasingly used as a service exposed via public APIs. At the same time, these encoder models are particularly vulnerable to model stealing attacks due to the high dimensionality of vector representations they output. Yet, encoders remain undefended: existing mitigation strategies for stealing attacks focus on supervised learning. We introduce a new dataset inference defense, which uses the private training set of the victim encoder model to attribute its ownership in the event of stealing. The intuition is that the log-likelihood of an encoder's output representations is higher on the victim's training data than on test data if it is stolen from the victim, but not if it is independently trained. We compute this log-likelihood using density estimation models. As part of our evaluation, we also propose measuring the fidelity of stolen encoders and quantifying the effectiveness of the theft detection without involving downstream tasks; instead, we leverage mutual information and distance measurements. Our extensive empirical results in the vision domain demonstrate that dataset inference is a promising direction for defending self-supervised models against model stealing.

ICLR Conference 2022 Conference Paper

Hyperparameter Tuning with Renyi Differential Privacy

Nicolas Papernot
Thomas Steinke 0002

For many differentially private algorithms, such as the prominent noisy stochastic gradient descent (DP-SGD), the analysis needed to bound the privacy leakage of a single training run is well understood. However, few studies have reasoned about the privacy leakage resulting from the multiple training runs needed to fine tune the value of the training algorithm’s hyperparameters. In this work, we first illustrate how simply setting hyperparameters based on non-private training runs can leak private information. Motivated by this observation, we then provide privacy guarantees for hyperparameter search procedures within the framework of Renyi Differential Privacy. Our results improve and extend the work of Liu and Talwar (STOC 2019). Our analysis supports our previous observation that tuning hyperparameters does indeed leak private information, but we prove that, under certain assumptions, this leakage is modest, as long as each candidate training run needed to select hyperparameters is itself differentially private.

NeurIPS Conference 2022 Conference Paper

In Differential Privacy, There is Truth: on Vote-Histogram Leakage in Ensemble Private Learning

Jiaqi Wang
Roei Schuster
I Shumailov
David Lie
Nicolas Papernot

When learning from sensitive data, care must be taken to ensure that training algorithms address privacy concerns. The canonical Private Aggregation of Teacher Ensembles, or PATE, computes output labels by aggregating the predictions of a (possibly distributed) collection of teacher models via a voting mechanism. The mechanism adds noise to attain a differential privacy guarantee with respect to the teachers' training data. In this work, we observe that this use of noise, which makes PATE predictions stochastic, enables new forms of leakage of sensitive information. For a given input, our adversary exploits this stochasticity to extract high-fidelity histograms of the votes submitted by the underlying teachers. From these histograms, the adversary can learn sensitive attributes of the input such as race, gender, or age. Although this attack does not directly violate the differential privacy guarantee, it clearly violates privacy norms and expectations, and would not be possible $\textit{at all}$ without the noise inserted to obtain differential privacy. In fact, counter-intuitively, the attack $\textbf{becomes easier as we add more noise}$ to provide stronger differential privacy. We hope this encourages future work to consider privacy holistically rather than treat differential privacy as a panacea.

ICLR Conference 2022 Conference Paper

Increasing the Cost of Model Extraction with Calibrated Proof of Work

Adam Dziedzic
Muhammad Ahmad Kaleem
Yu Shen Lu
Nicolas Papernot

In model extraction attacks, adversaries can steal a machine learning model exposed via a public API by repeatedly querying it and adjusting their own model based on obtained predictions. To prevent model stealing, existing defenses focus on detecting malicious queries, truncating, or distorting outputs, thus necessarily introducing a tradeoff between robustness and model utility for legitimate users. Instead, we propose to impede model extraction by requiring users to complete a proof-of-work before they can read the model's predictions. This deters attackers by greatly increasing (even up to 100x) the computational effort needed to leverage query access for model extraction. Since we calibrate the effort required to complete the proof-of-work to each query, this only introduces a slight overhead for regular users (up to 2x). To achieve this, our calibration applies tools from differential privacy to measure the information revealed by a query. Our method requires no modification of the victim model and can be applied by machine learning practitioners to guard their publicly exposed models against being easily stolen.

ICLR Conference 2022 Conference Paper

Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning

Natalie Dullerud
Karsten Roth
Kimia Hamidieh
Nicolas Papernot
Marzyeh Ghassemi

Deep metric learning (DML) enables learning with less supervision through its emphasis on the similarity structure of representations. There has been much work on improving generalization of DML in settings like zero-shot retrieval, but little is known about its implications for fairness. In this paper, we are the first to evaluate state-of-the-art DML methods trained on imbalanced data, and to show the negative impact these representations have on minority subgroup performance when used for downstream tasks. In this work, we first define fairness in DML through an analysis of three properties of the representation space -- inter-class alignment, intra-class alignment, and uniformity -- and propose \textit{\textbf{finDML}}, the \textit{\textbf{f}}airness \textit{\textbf{i}}n \textit{\textbf{n}}on-balanced \textit{\textbf{DML}} benchmark to characterize representation fairness. Utilizing \textit{finDML}, we find bias in DML representations to propagate to common downstream classification tasks. Surprisingly, this bias is propagated even when training data in the downstream task is re-balanced. To address this problem, we present Partial Attribute De-correlation (\textit{\textbf{\pad}}) to disentangle feature representations from sensitive attributes and reduce performance gaps between subgroups in both embedding space and downstream metrics.

ICML Conference 2022 Conference Paper

On the Difficulty of Defending Self-Supervised Learning against Model Extraction

Adam Dziedzic
Nikita Dhawan
Muhammad Ahmad Kaleem
Jonas Guan
Nicolas Papernot

Self-Supervised Learning (SSL) is an increasingly popular ML paradigm that trains models to transform complex inputs into representations without relying on explicit labels. These representations encode similarity structures that enable efficient learning of multiple downstream tasks. Recently, ML-as-a-Service providers have commenced offering trained SSL models over inference APIs, which transform user inputs into useful representations for a fee. However, the high cost involved to train these models and their exposure over APIs both make black-box extraction a realistic security threat. We thus explore model stealing attacks against SSL. Unlike traditional model extraction on classifiers that output labels, the victim models here output representations; these representations are of significantly higher dimensionality compared to the low-dimensional prediction scores output by classifiers. We construct several novel attacks and find that approaches that train directly on a victim’s stolen representations are query efficient and enable high accuracy for downstream models. We then show that existing defenses against model extraction are inadequate and not easily retrofitted to the specificities of SSL.

NeurIPS Conference 2022 Conference Paper

On the Limitations of Stochastic Pre-processing Defenses

Yue Gao
I Shumailov
Kassem Fawaz
Nicolas Papernot

Defending against adversarial examples remains an open problem. A common belief is that randomness at inference increases the cost of finding adversarial inputs. An example of such a defense is to apply a random transformation to inputs prior to feeding them to the model. In this paper, we empirically and theoretically investigate such stochastic pre-processing defenses and demonstrate that they are flawed. First, we show that most stochastic defenses are weaker than previously thought; they lack sufficient randomness to withstand even standard attacks like projected gradient descent. This casts doubt on a long-held assumption that stochastic defenses invalidate attacks designed to evade deterministic defenses and force attackers to integrate the Expectation over Transformation (EOT) concept. Second, we show that stochastic defenses confront a trade-off between adversarial robustness and model invariance; they become less effective as the defended model acquires more invariance to their randomization. Future work will need to decouple these two effects. We also discuss implications and guidance for future research.

NeurIPS Conference 2022 Conference Paper

The Privacy Onion Effect: Memorization is Relative

Nicholas Carlini
Matthew Jagielski
Chiyuan Zhang
Nicolas Papernot
Andreas Terzis
Florian Tramer

Machine learning models trained on private datasets have been shown to leak their private data. Recent work has found that the average data point is rarely leaked---it is often the outlier samples that are subject to memorization and, consequently, leakage. We demonstrate and analyze an Onion Effect of memorization: removing the "layer" of outlier points that are most vulnerable to a privacy attack exposes a new layer of previously-safe points to the same attack. We perform several experiments that are consistent with this hypothesis. For example, we show that for membership inference attacks, when the layer of easiest-to-attack examples is removed, another layer below becomes easy-to-attack. The existence of this effect has various consequences. For example, it suggests that proposals to defend against memorization without training with rigorous privacy guarantees are unlikely to be effective. Further, it suggests that privacy-enhancing technologies such as machine unlearning could actually harm the privacy of other users.

NeurIPS Conference 2022 Conference Paper

Washing The Unwashable : On The (Im)possibility of Fairwashing Detection

Ali Shahin Shamsabadi
Mohammad Yaghini
Natalie Dullerud
Sierra Wyllie
Ulrich Aïvodji
Aisha Alaagib
Sébastien Gambs
Nicolas Papernot

The use of black-box models (e. g. , deep neural networks) in high-stakes decision-making systems, whose internal logic is complex, raises the need for providing explanations about their decisions. Model explanation techniques mitigate this problem by generating an interpretable and high-fidelity surrogate model (e. g. , a logistic regressor or decision tree) to explain the logic of black-box models. In this work, we investigate the issue of fairwashing, in which model explanation techniques are manipulated to rationalize decisions taken by an unfair black-box model using deceptive surrogate models. More precisely, we theoretically characterize and analyze fairwashing, proving that this phenomenon is difficult to avoid due to an irreducible factor---the unfairness of the black-box model. Based on the theory developed, we propose a novel technique, called FRAUD-Detect (FaiRness AUDit Detection), to detect fairwashed models by measuring a divergence over subpopulation-wise fidelity measures of the interpretable model. We empirically demonstrate that this divergence is significantly larger in purposefully fairwashed interpretable models than in honest ones. Furthermore, we show that our detector is robust to an informed adversary trying to bypass our detector. The code implementing FRAUD-Detect is available at https: //github. com/cleverhans-lab/FRAUD-Detect.

ICLR Conference 2021 Conference Paper

CaPC Learning: Confidential and Private Collaborative Learning

Christopher A. Choquette-Choo
Natalie Dullerud
Adam Dziedzic
Yunxiang Zhang 0003
Somesh Jha
Nicolas Papernot
Xiao Wang 0012

Machine learning benefits from large training datasets, which may not always be possible to collect by any single entity, especially when using privacy-sensitive data. In many contexts, such as healthcare and finance, separate parties may wish to collaborate and learn from each other's data but are prevented from doing so due to privacy regulations. Some regulations prevent explicit sharing of data between parties by joining datasets in a central location (confidentiality). Others also limit implicit sharing of data, e.g., through model predictions (privacy). There is currently no method that enables machine learning in such a setting, where both confidentiality and privacy need to be preserved, to prevent both explicit and implicit sharing of data. Federated learning only provides confidentiality, not privacy, since gradients shared still contain private information. Differentially private learning assumes unreasonably large datasets. Furthermore, both of these learning paradigms produce a central model whose architecture was previously agreed upon by all parties rather than enabling collaborative learning where each party learns and improves their own local model. We introduce Confidential and Private Collaborative (CaPC) learning, the first method provably achieving both confidentiality and privacy in a collaborative setting. We leverage secure multi-party computation (MPC), homomorphic encryption (HE), and other techniques in combination with privately aggregated teacher models. We demonstrate how CaPC allows participants to collaborate without having to explicitly join their training sets or train a central model. Each party is able to improve the accuracy and fairness of their model, even in settings where each party has a model that performs well on their own dataset or when datasets are not IID and model architectures are heterogeneous across parties.

ICLR Conference 2021 Conference Paper

Dataset Inference: Ownership Resolution in Machine Learning

Pratyush Maini
Mohammad Yaghini
Nicolas Papernot

With increasingly more data and computation involved in their training, machine learning models constitute valuable intellectual property. This has spurred interest in model stealing, which is made more practical by advances in learning with partial, little, or no supervision. Existing defenses focus on inserting unique watermarks in a model's decision surface, but this is insufficient: the watermarks are not sampled from the training distribution and thus are not always preserved during model stealing. In this paper, we make the key observation that knowledge contained in the stolen model's training set is what is common to all stolen copies. The adversary's goal, irrespective of the attack employed, is always to extract this knowledge or its by-products. This gives the original model's owner a strong advantage over the adversary: model owners have access to the original training data. We thus introduce $\textit{dataset inference}$, the process of identifying whether a suspected model copy has private knowledge from the original model's dataset, as a defense against model stealing. We develop an approach for dataset inference that combines statistical testing with the ability to estimate the distance of multiple data points to the decision boundary. Our experiments on CIFAR10, SVHN, CIFAR100 and ImageNet show that model owners can claim with confidence greater than 99% that their model (or dataset as a matter of fact) was stolen, despite only exposing 50 of the stolen model's training points. Dataset inference defends against state-of-the-art attacks even when the adversary is adaptive. Unlike prior work, it does not require retraining or overfitting the defended model.

ICML Conference 2021 Conference Paper

Label-Only Membership Inference Attacks

Christopher A. Choquette-Choo
Florian Tramèr
Nicholas Carlini
Nicolas Papernot

Membership inference is one of the simplest privacy threats faced by machine learning models that are trained on private sensitive data. In this attack, an adversary infers whether a particular point was used to train the model, or not, by observing the model’s predictions. Whereas current attack methods all require access to the model’s predicted confidence score, we introduce a label-only attack that instead evaluates the robustness of the model’s predicted (hard) labels under perturbations of the input, to infer membership. Our label-only attack is not only as-effective as attacks requiring access to confidence scores, it also demonstrates that a class of defenses against membership inference, which we call “confidence masking” because they obfuscate the confidence scores to thwart attacks, are insufficient to prevent the leakage of private information. Our experiments show that training with differential privacy or strong L2 regularization are the only current defenses that meaningfully decrease leakage of private information, even for points that are outliers of the training distribution.

NeurIPS Conference 2021 Conference Paper

Manipulating SGD with Data Ordering Attacks

I Shumailov
Zakhar Shumaylov
Dmitry Kazhdan
Yiren Zhao
Nicolas Papernot
Murat A. Erdogdu
Ross J Anderson

Machine learning is vulnerable to a wide variety of attacks. It is now well understood that by changing the underlying data distribution, an adversary can poison the model trained with it or introduce backdoors. In this paper we present a novel class of training-time attacks that require no changes to the underlying dataset or model architecture, but instead only change the order in which data are supplied to the model. In particular, we find that the attacker can either prevent the model from learning, or poison it to learn behaviours specified by the attacker. Furthermore, we find that even a single adversarially-ordered epoch can be enough to slow down model learning, or even to reset all of the learning progress. Indeed, the attacks presented here are not specific to the model or dataset, but rather target the stochastic nature of modern learning procedures. We extensively evaluate our attacks on computer vision and natural language benchmarks to find that the adversary can disrupt model training and even introduce backdoors.

ICML Conference 2021 Conference Paper

Markpainting: Adversarial Machine Learning meets Inpainting

David Khachaturov
Ilia Shumailov
Yiren Zhao
Nicolas Papernot
Ross J. Anderson

Inpainting is a learned interpolation technique that is based on generative modeling and used to populate masked or missing pieces in an image; it has wide applications in picture editing and retouching. Recently, inpainting started being used for watermark removal, raising concerns. In this paper we study how to manipulate it using our markpainting technique. First, we show how an image owner with access to an inpainting model can augment their image in such a way that any attempt to edit it using that model will add arbitrary visible information. We find that we can target multiple different models simultaneously with our technique. This can be designed to reconstitute a watermark if the editor had been trying to remove it. Second, we show that our markpainting technique is transferable to models that have different architectures or were trained on different datasets, so watermarks created using it are difficult for adversaries to remove. Markpainting is novel and can be used as a manipulation alarm that becomes visible in the event of inpainting. Source code is available at: https: //github. com/iliaishacked/markpainting.

AAAI Conference 2021 Conference Paper

Tempered Sigmoid Activations for Deep Learning with Differential Privacy

Nicolas Papernot
Abhradeep Thakurta
Shuang Song
Steve Chien
Úlfar Erlingsson

Because learning sometimes involves sensitive data, machine learning algorithms have been extended to offer differential privacy for training data. In practice, this has been mostly an afterthought, with privacy-preserving models obtained by re-running training with a different optimizer, but using the model architectures that already performed well in a nonprivacy-preserving setting. This approach leads to less than ideal privacy/utility tradeoffs, as we show here. To improve these tradeoffs, prior work introduces variants of differential privacy that weaken the privacy guarantee proved to increase model utility. We show this is not necessary and instead propose that utility be improved by choosing activation functions designed explicitly for privacy-preserving training. A crucial operation in differentially private SGD is gradient clipping, which along with modifying the optimization path (at times resulting in not-optimizing a single objective function), may also introduce both significant bias and variance to the learning process. We empirically identify exploding gradients arising from ReLU may be one of the main sources of this. We demonstrate analytically and experimentally how a general family of bounded activation functions, the tempered sigmoids, consistently outperform the currently established choice: unbounded activation functions like ReLU. Using this paradigm, we achieve new state-of-the-art accuracy on MNIST, FashionMNIST, and CIFAR10 without any modification of the learning procedure fundamentals or differential privacy analysis. While the changes we make are simple in retrospect, the simplicity of our approach facilitates its implementation and adoption to meaningfully improve state-of-the-art machine learning while still providing strong guarantees in the original framework of differential privacy.

ICML Conference 2020 Conference Paper

Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations

Florian Tramèr
Jens Behrmann
Nicholas Carlini
Nicolas Papernot
Jörn-Henrik Jacobsen

Adversarial examples are malicious inputs crafted to induce misclassification. Commonly studied \emph{sensitivity-based} adversarial examples introduce semantically-small changes to an input that result in a different model prediction. This paper studies a complementary failure mode, \emph{invariance-based} adversarial examples, that introduce minimal semantic changes that modify an input’s true label yet preserve the model’s prediction. We demonstrate fundamental tradeoffs between these two types of adversarial examples. We show that defenses against sensitivity-based attacks actively harm a model’s accuracy on invariance-based attacks, and that new approaches are needed to resist both attack types. In particular, we break state-of-the-art adversarially-trained and \emph{certifiably-robust} models by generating small perturbations that the models are (provably) robust to, yet that change an input’s class according to human labelers. Finally, we formally show that the existence of excessively invariant classifiers arises from the presence of \emph{overly-robust} predictive features in standard datasets.

ICLR Conference 2020 Conference Paper

Thieves on Sesame Street! Model Extraction of BERT-based APIs

Kalpesh Krishna
Gaurav Singh Tomar
Ankur P. Parikh
Nicolas Papernot
Mohit Iyyer

We study the problem of model extraction in natural language processing, in which an adversary with only query access to a victim model attempts to reconstruct a local copy of that model. Assuming that both the adversary and victim model fine-tune a large pretrained language model such as BERT (Devlin et al., 2019), we show that the adversary does not need any real training data to successfully mount the attack. In fact, the attacker need not even use grammatical or semantically meaningful queries: we show that random sequences of words coupled with task-specific heuristics form effective queries for model extraction on a diverse set of NLP tasks, including natural language inference and question answering. Our work thus highlights an exploit only made feasible by the shift towards transfer learning methods within the NLP community: for a query budget of a few hundred dollars, an attacker can extract a model that performs only slightly worse than the victim model. Finally, we study two defense strategies against model extraction—membership classification and API watermarking—which while successful against some adversaries can also be circumvented by more clever ones.

ICML Conference 2019 Conference Paper

Analyzing and Improving Representations with the Soft Nearest Neighbor Loss

Nicholas Frosst
Nicolas Papernot
Geoffrey E. Hinton

We explore and expand the Soft Nearest Neighbor Loss to measure the entanglement of class manifolds in representation space: i. e. , how close pairs of points from the same class are relative to pairs of points from different classes. We demonstrate several use cases of the loss. As an analytical tool, it provides insights into the evolution of class similarity structures during learning. Surprisingly, we find that maximizing the entanglement of representations of different classes in the hidden layers is beneficial for discrimination in the final layer, possibly because it encourages representations to identify class-independent similarity structures. Maximizing the soft nearest neighbor loss in the hidden layers leads not only to better-calibrated estimates of uncertainty on outlier data but also marginally improved generalization. Data that is not from the training distribution can be recognized by observing that in the hidden layers, it has fewer than the normal number of neighbors from the predicted class.

NeurIPS Conference 2019 Conference Paper

MixMatch: A Holistic Approach to Semi-Supervised Learning

David Berthelot
Nicholas Carlini
Ian Goodfellow
Nicolas Papernot
Avital Oliver
Colin Raffel

Semi-supervised learning has proven to be a powerful paradigm for leveraging unlabeled data to mitigate the reliance on large labeled datasets. In this work, we unify the current dominant approaches for semi-supervised learning to produce a new algorithm, MixMatch, that guesses low-entropy labels for data-augmented unlabeled examples and mixes labeled and unlabeled data using MixUp. MixMatch obtains state-of-the-art results by a large margin across many datasets and labeled data amounts. For example, on CIFAR-10 with 250 labels, we reduce error rate by a factor of 4 (from 38% to 11%) and by a factor of 2 on STL-10. We also demonstrate how MixMatch can help achieve a dramatically better accuracy-privacy trade-off for differential privacy. Finally, we perform an ablation study to tease apart which components of MixMatch are most important for its success. Code is attached.

NeurIPS Conference 2018 Conference Paper

Adversarial Examples that Fool both Computer Vision and Time-Limited Humans

Gamaleldin Elsayed
Shreya Shankar
Brian Cheung
Nicolas Papernot
Alexey Kurakin
Ian Goodfellow
Jascha Sohl-Dickstein

Machine learning models are vulnerable to adversarial examples: small changes to images can cause computer vision models to make mistakes such as identifying a school bus as an ostrich. However, it is still an open question whether humans are prone to similar mistakes. Here, we address this question by leveraging recent techniques that transfer adversarial examples from computer vision models with known parameters and architecture to other models with unknown parameters and architecture, and by matching the initial processing of the human visual system. We find that adversarial examples that strongly transfer across computer vision models influence the classifications made by time-limited human observers.

ICLR Conference 2018 Conference Paper

Scalable Private Learning with PATE

Nicolas Papernot
Shuang Song 0001
Ilya Mironov
Ananth Raghunathan
Kunal Talwar
Úlfar Erlingsson

The rapid adoption of machine learning has increased concerns about the privacy implications of machine learning models trained on sensitive data, such as medical records or other personal information. To address those concerns, one promising approach is Private Aggregation of Teacher Ensembles, or PATE, which transfers to a "student" model the knowledge of an ensemble of "teacher" models, with intuitive privacy provided by training teachers on disjoint data and strong privacy guaranteed by noisy aggregation of teachers’ answers. However, PATE has so far been evaluated only on simple classification tasks like MNIST, leaving unclear its utility when applied to larger-scale learning tasks and real-world datasets. In this work, we show how PATE can scale to learning tasks with large numbers of output classes and uncurated, imbalanced training data with errors. For this, we introduce new noisy aggregation mechanisms for teacher ensembles that are more selective and add less noise, and prove their tighter differential-privacy guarantees. Our new mechanisms build on two insights: the chance of teacher consensus is increased by using more concentrated noise and, lacking consensus, no answer need be given to a student. The consensus answers used are more likely to be correct, offer better intuitive privacy, and incur lower-differential privacy cost. Our evaluation shows our mechanisms improve on the original PATE on all measures, and scale to larger tasks with both high utility and very strong privacy (ε < 1.0).

ICLR Conference 2017 Conference Paper

Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data

Nicolas Papernot
Martín Abadi
Úlfar Erlingsson
Ian J. Goodfellow
Kunal Talwar

Some machine learning applications involve training data that is sensitive, such as the medical histories of patients in a clinical trial. A model may inadvertently and implicitly store some of its training data; careful analysis of the model may therefore reveal sensitive information. To address this problem, we demonstrate a generally applicable approach to providing strong privacy guarantees for training data: Private Aggregation of Teacher Ensembles (PATE). The approach combines, in a black-box fashion, multiple models trained with disjoint datasets, such as records from different subsets of users. Because they rely directly on sensitive data, these models are not published, but instead used as ''teachers'' for a ''student'' model. The student learns to predict an output chosen by noisy voting among all of the teachers, and cannot directly access an individual teacher or the underlying data or parameters. The student's privacy properties can be understood both intuitively (since no single teacher and thus no single dataset dictates the student's training) and formally, in terms of differential privacy. These properties hold even if an adversary can not only query the student but also inspect its internal workings. Compared with previous work, the approach imposes only weak assumptions on how teachers are trained: it applies to any model, including non-convex models like DNNs. We achieve state-of-the-art privacy/utility trade-offs on MNIST and SVHN thanks to an improved privacy analysis and semi-supervised learning.