Author name cluster

Ananthram Swami

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.

8 papers

2 author rows

ICLR Conference 2025 Conference Paper

On the Adversarial Vulnerability of Label-Free Test-Time Adaptation

Shahriar Rifat
Jonathan D. Ashdown
Michael J. De Lucia
Ananthram Swami
Francesco Restuccia 0001

Despite the success of Test-time adaptation (TTA), recent work has shown that adding relatively small adversarial perturbations to a limited number of samples leads to significant performance degradation. Therefore, it is crucial to rigorously evaluate existing TTA algorithms against relevant threats and implement appropriate security countermeasures. Importantly, existing threat models assume test-time samples will be labeled, which is impractical in real-world scenarios. To address this gap, we propose a new attack algorithm that does not rely on access to labeled test samples, thus providing a concrete way to assess the security vulnerabilities of TTA algorithms. Our attack design is grounded in theoretical foundations and can generate strong attacks against different state of the art TTA methods. In addition, we show that existing defense mechanisms are almost ineffective, which emphasizes the need for further research on TTA security. Through extensive experiments on CIFAR10-C, CIFAR100-C, and ImageNet-C, we demonstrate that our proposed approach closely matches the performance of state-of-the-art attack benchmarks, even without access to labeled samples. In certain cases, our approach generates stronger attacks, e.g., more than 4% higher error rate on CIFAR10-C.

Details

ICLR Conference 2023 Conference Paper

Graph-based Deterministic Policy Gradient for Repetitive Combinatorial Optimization Problems

Zhongyuan Zhao 0002
Ananthram Swami
Santiago Segarra

We propose an actor-critic framework for graph-based machine learning pipelines with non-differentiable blocks, and apply it to repetitive combinatorial optimization problems (COPs) under hard constraints. Repetitive COP refers to problems to be solved repeatedly on graphs of the same or slowly changing topology but rapidly changing node or edge weights. Compared to one-shot COPs, repetitive COPs often rely on fast heuristics to solve one instance of the problem before the next one arrives, at the cost of a relatively large optimality gap. Through numerical experiments on several discrete optimization problems, we show that our approach can learn reusable node or edge representations to reduce the optimality gap of fast heuristics for independent repetitive COPs, and can optimize the long-term objectives for repetitive COPs embedded in graph-based Markov decision processes. Source code at https://github.com/XzrTGMu/twin-nphard

Details

AAMAS Conference 2023 Conference Paper

The Influence Maximisation Game

Sukankana Chakraborty
Sebastian Stein
Ananthram Swami
Matthew Jones
Lewis Hill

The problem of influence maximisation investigates efficient ways in which external influence (typically limited by resources) can be applied to a social network to maximise control over the global behaviours of a population. It is an effective tool that finds its application in many real-world scenarios, for instance it can be used to gather intelligence in crowdsourcing activities and to incentivise people to adopt desirable public policies. While the problem has been studied extensively in theoretical settings, many of these approaches can be expensive and inefficient to apply in the real world, particularly when considering an unknown or irrational competitor. The influence maximisation game was designed to bridge this gap between theory and the practical application of this knowledge. In this experiment, human subjects are presented with networks where they can employ their own tactics to maintain maximum influence against a competitor (which in this case is an AI agent). We aim to determine how people strategise to spread influence in the real world. In particular, we determine if people always act rationally in these settings or if their strategies are inherently biased —in which case we aim to identify inexpensive, yet effective strategies that can outperform these biased strategies. Observing how people strategise in the real world can help us modify our theoretical results for more efficient practical applications.

PDF

NeurIPS Conference 2022 Conference Paper

Physics-Informed Implicit Representations of Equilibrium Network Flows

Kevin D. Smith
Francesco Seccamonte
Ananthram Swami
Francesco Bullo

Flow networks are ubiquitous in natural and engineered systems, and in order to understand and manage these networks, one must quantify the flow of commodities across their edges. This paper considers the estimation problem of predicting unlabeled edge flows from nodal supply and demand. We propose an implicit neural network layer that incorporates two fundamental physical laws: conservation of mass, and the existence of a constitutive relationship between edge flows and nodal states (e. g. , Ohm's law). Computing the edge flows from these two laws is a nonlinear inverse problem, which our layer solves efficiently with a specialized contraction mapping. Using implicit differentiation to compute the solution's gradients, our model is able to learn the constitutive relationship within a semi-supervised framework. We demonstrate that our approach can accurately predict edge flows in several experiments on AC power networks and water distribution systems.

PDF Details

ICLR Conference 2021 Conference Paper

Combining Physics and Machine Learning for Network Flow Estimation

Arlei Lopes da Silva
Furkan Kocayusufoglu
Saber Jafarpour
Francesco Bullo
Ananthram Swami
Ambuj K. Singh

The flow estimation problem consists of predicting missing edge flows in a network (e.g., traffic, power, and water) based on partial observations. These missing flows depend both on the underlying \textit{physics} (edge features and a flow conservation law) as well as the observed edge flows. This paper introduces an optimization framework for computing missing edge flows and solves the problem using bilevel optimization and deep learning. More specifically, we learn regularizers that depend on edge features (e.g., number of lanes in a road, the resistance of a power line) using neural networks. Empirical results show that our method accurately predicts missing flows, outperforming the best baseline, and is able to capture relevant physical properties in traffic and power networks.

Details

NeurIPS Conference 2020 Conference Paper

Unsupervised Joint k-node Graph Representations with Compositional Energy-Based Models

Leonardo Cotta
Carlos H. C. Teixeira
Ananthram Swami
Bruno Ribeiro

Existing Graph Neural Network (GNN) methods that learn inductive unsupervised graph representations focus on learning node and edge representations by predicting observed edges in the graph. Although such approaches have shown advances in downstream node classification tasks, they are ineffective in jointly representing larger k-node sets, k{>}2. We propose MHM-GNN, an inductive unsupervised graph representation approach that combines joint k-node representations with energy-based models (hypergraph Markov networks) and GNNs. To address the intractability of the loss that arises from this combination, we endow our optimization with a loss upper bound using a finite-sample unbiased Markov Chain Monte Carlo estimator. Our experiments show that the unsupervised joint k-node representations of MHM-GNN produce better unsupervised representations than existing approaches from the literature.

PDF Details

NeurIPS Conference 2019 Conference Paper

Attribution-Based Confidence Metric For Deep Neural Networks

Susmit Jha
Sunny Raj
Steven Fernandes
Sumit Jha
Somesh Jha
Brian Jalaian
Gunjan Verma
Ananthram Swami

We propose a novel confidence metric, namely, attribution-based confidence (ABC) for deep neural networks (DNNs). ABC metric characterizes whether the output of a DNN on an input can be trusted. DNNs are known to be brittle on inputs outside the training distribution and are, hence, susceptible to adversarial attacks. This fragility is compounded by a lack of effectively computable measures of model confidence that correlate well with the accuracy of DNNs. These factors have impeded the adoption of DNNs in high-assurance systems. The proposed ABC metric addresses these challenges. It does not require access to the training data, the use of ensembles, or the need to train a calibration model on a held-out validation set. Hence, the new metric is usable even when only a trained model is available for inference. We mathematically motivate the proposed metric and evaluate its effectiveness with two sets of experiments. First, we study the change in accuracy and the associated confidence over out-of-distribution inputs. Second, we consider several digital and physically realizable attacks such as FGSM, CW, DeepFool, PGD, and adversarial patch generation methods. The ABC metric is low on out-of-distribution data and adversarial examples, where the accuracy of the model is also low. These experiments demonstrate the effectiveness of the ABC metric to make DNNs more trustworthy and resilient.

PDF Details

NeurIPS Conference 2019 Conference Paper

Error Correcting Output Codes Improve Probability Estimation and Adversarial Robustness of Deep Neural Networks

Gunjan Verma
Ananthram Swami

Modern machine learning systems are susceptible to adversarial examples; inputs which clearly preserve the characteristic semantics of a given class, but whose classification is (usually confidently) incorrect. Existing approaches to adversarial defense generally rely on modifying the input, e. g. quantization, or the learned model parameters, e. g. via adversarial training. However, recent research has shown that most such approaches succumb to adversarial examples when different norms or more sophisticated adaptive attacks are considered. In this paper, we propose a fundamentally different approach which instead changes the way the output is represented and decoded. This simple approach achieves state-of-the-art robustness to adversarial examples for L 2 and L ∞ based adversarial perturbations on MNIST and CIFAR10. In addition, even under strong white-box attacks, we find that our model often assigns adversarial examples a low probability; those with high probability are usually interpretable, i. e. perturbed towards the perceptual boundary between the original and adversarial class. Our approach has several advantages: it yields more meaningful probability estimates, is extremely fast during training and testing, requires essentially no architectural changes to existing discriminative learning pipelines, is wholly complementary to other defense approaches including adversarial training, and does not sacrifice benign test set performance

PDF Details