arXiv research

New adversarial examples with structured distortion sets improve robustness and perceptibility.

A new model for sequential prediction handles adversarial examples by allowing abstention.

New framework for understanding adversarial and stochastic learning.

Modern machine learning algorithms perform poorly on adversarially manipulated data. Adversarial risk quantifies the error of classifiers in adversarial settings; adversarial classifiers minimize adversarial risk. In this paper, we analyze adversarial risk and adversarial classifiers from an optimal transport perspecti…

Modern deep neural network models suffer from adversarial examples, i.e. confidently misclassified points in the input space. It has been shown that Bayesian neural networks are a promising approach for detecting adversarial points, but careful analysis is problematic due to the complexity of these models. Recently Gil…

Study shows adversarial attacks can fool speech-to-text models, and PCA is ineffective as a defense.

Study robustness of split conformal prediction under adversarial attacks.

We present heuristics for solving the maximin problem induced by the generative adversarial privacy setting for linear and convolutional neural network (CNN) adversaries. In the linear adversary setting, we present a greedy algorithm for approximating the optimal solution for the privatizer, which performs better as th…

Study proves existence of robust classifiers in multiclass adversarial training.

This paper examines various definitions of adversarial risk and their implications.

This paper analyzes how machine learning models resist adversarial attacks in nonparametric regression.

Study efficient learning of robust halfspaces with noise.

We improve adversarial robustness calibration analysis for broader hypothesis sets.

Improved online convex optimization bounds between stochastic and adversarial settings.

Adversarial robust learning improved for transductive setting.

Robust RL with learned optimal adversary improves agent performance under adversarial state observations.

New bounds for online convex optimization between stochastic and adversarial settings.

Study improves resilience against adversarial clean-label attacks in real and noisy settings.

Paper examines Go AI robustness against adversarial attacks.

Adversarial attacks against neural networks in a regression setting are a critical yet understudied problem. In this work, we advance the state of the art by investigating adversarial attacks against regression networks and by formulating a more effective defense against these attacks. In particular, we take the perspe…

Study robust regression learning under adversarial attacks.

In recent years, different types of adversarial examples from different fields have emerged endlessly, including purely natural ones without perturbations. A variety of defenses are proposed and then broken quickly. Two fundamental questions need to be asked: What's the reason for the existence of adversarial examples …

Study robust learning without knowing perturbation sets, using interactions with attackers.

Paper bounds convergence rate of adversarial surrogate risk.

The paper sets lower bounds for adversarial robustness in multiclass classification.

Adversarial training achieves optimal test error for shallow networks.

Study adversarial perturbations in classification, analyzing learning and certification.

Study on Pareto optimality in multi-objective bandit problems.

Adversarial examples pose a threat to deep neural network models in a variety of scenarios, from settings where the adversary has complete knowledge of the model and to the opposite "black box" setting. Black box attacks are particularly threatening as the adversary only needs access to the input and output of the mode…

We consider the problem of influence maximization in fixed networks for contagion models in an adversarial setting. The goal is to select an optimal set of nodes to seed the influence process, such that the number of influenced nodes at the conclusion of the campaign is as large as possible. We formulate the problem as…

Improved FPL algorithms for adversarial MDPs with better regret bounds.

Algorithm learns expert weights to minimize regret in adversarial setting.

New framework for fair classification in adversarial settings with provable guarantees.

Paper provides robustness bounds for GNNs against adversarial attacks.

The paper shows how policy regularization acts like an adversary to improve robustness.

New gradient coding schemes reduce decoding error in both random and adversarial straggler settings.

Deep neural networks are vulnerable to adversarial examples. Prior defenses attempted to make deep networks more robust by either changing the network architecture or augmenting the training set with adversarial examples, but both have inherent limitations. Motivated by recent research that shows outliers in the traini…

We consider the problem of controlling a possibly unknown linear dynamical system with adversarial perturbations, adversarially chosen convex loss functions, and partially observed states, known as non-stochastic control. We introduce a controller parametrization based on the denoised observations, and prove that apply…

Deep neural networks (DNNs) have set benchmarks on a wide array of supervised learning tasks. Trained DNNs, however, often lack robustness to minor adversarial perturbations to the input, which undermines their true practicality. Recent works have increased the robustness of DNNs by fitting networks using adversarially…

New insights link no-regret learning to online conformal prediction in adversarial settings.

Most state-of-the-art machine learning (ML) classification systems are vulnerable to adversarial perturbations. As a consequence, adversarial robustness poses a significant challenge for the deployment of ML-based systems in safety- and security-critical environments like autonomous driving, disease detection or unmann…

This paper explores tradeoffs between standard and adversarial risks in distributionally adversarial training.

Adapting Hedge algorithm for semi-adversarial data with root-entropy regularization.

Paper provides optimal statistical guarantees for adversarial robustness in Gaussian classification.

Many machine learning models are vulnerable to adversarial attacks; for example, adding adversarial perturbations that are imperceptible to humans can often make machine learning models produce wrong predictions with high confidence. Moreover, although we may obtain robust models on the training dataset via adversarial…

Note that this paper is superceded by "Black-Box Adversarial Attacks with Limited Queries and Information." Current neural network-based image classifiers are susceptible to adversarial examples, even in the black-box setting, where the attacker is limited to query access without access to gradients. Previous methods -…

Adversarial training shows promise as an approach for training models that are robust towards adversarial perturbation. In this paper, we explore some of the practical challenges of adversarial training. We present a sensitivity analysis that illustrates that the effectiveness of adversarial training hinges on the sett…

This paper optimizes attacks on stochastic bandits and proposes defenses against them.