The problem of Byzantine resilience in distributed machine learning, aka Byzantine machine
learning, consists of designing distributed algorithms that can train an accurate model …

Adversarial risk quantifies the performance of classifiers on adversarially perturbed data.
Numerous definitions of adversarial risk---not all mathematically rigorous and differing subtly …

We study a family of adversarial multiclass classification problems and provide equivalent
reformulations in terms of: 1) a family of generalized barycenter problems introduced in the …

We establish an equivalence between a family of adversarial training problems for non-
parametric binary classification and a family of regularized risk minimization problems where …

Several recent works in machine learning have focused on evaluating the test-time
robustness of a classifier: how well the classifier performs not just on the target domain it …

Given the widespread deployment of machine learning algorithms, the security of these
algorithms and thus, the field of adversarial machine learning gained popularity in the …

Adversarial training is a standard technique for training adversarially robust models. In this
paper, we study adversarial training as an alternating best-response strategy in a 2-player …

Black-box adversarial attacks designing adversarial examples for unseen deep neural
networks (DNNs) have received great attention over the past years. However, the underlying …

Several recent works have studied the societal effects of AI; these include issues such as
fairness, robustness, and safety. In many of these objectives, a learner seeks to minimize its …

Adversarial training is a min-max optimization problem that is designed to construct robust
classifiers against adversarial perturbations of data. We study three models of adversarial …