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

Deep learning has presented remarkable progress in various tasks. Despite the excellent
performance, deep learning models remain not robust, especially to well-designed …

Current methods for training robust networks lead to a drop in test accuracy, which has led
prior works to posit that a robustness-accuracy tradeoff may be inevitable in deep learning …

Numerous deep learning algorithms have been inspired by and understood via the notion of
information bottleneck, where unnecessary information is (often implicitly) minimized while …

Abstract 3D point cloud classification has many safety-critical applications such as
autonomous driving and robotic grasping. However, several studies showed that it is …

The Lipschitz constant of neural networks has been established as a key quantity to enforce
the robustness to adversarial examples. In this paper, we tackle the problem of building $1 …

A variety of fairness constraints have been proposed in the literature to mitigate group-level
statistical bias. Their impacts have been largely evaluated for different groups of populations …

It is well-known that classifiers are vulnerable to adversarial perturbations. To defend
against adversarial perturbations, various certified robustness results have been derived …

While deep neural networks have been achieving state-of-the-art performance across a
wide variety of applications, their vulnerability to adversarial attacks limits their widespread …

Due to the broad range of applications of reinforcement learning (RL), understanding the
effects of adversarial attacks against RL model is essential for the safe applications of this …