State-of-the-art classifiers have been shown to be largely vulnerable to adversarial
perturbations. One of the most effective strategies to improve robustness is adversarial …

We study adversarial robustness of neural networks from a margin maximization
perspective, where margins are defined as the distances from inputs to a classifier's decision …

While adversarial training has become the de facto approach for training robust classifiers, it
leads to a drop in accuracy. This has led to prior works postulating that accuracy is …

Adversarial training (AT) has become the de-facto standard to obtain models robust against
adversarial examples. However, AT exhibits severe robust overfitting: cross-entropy loss on …

Despite the empirical success of using adversarial training to defend deep learning models
against adversarial perturbations, so far, it still remains rather unclear what the principles are …

Despite achieving impressive performance, state-of-the-art classifiers remain highly
vulnerable to small, imperceptible, adversarial perturbations. This vulnerability has proven …

Obtaining deep networks that are robust against adversarial examples and generalize well
is an open problem. A recent hypothesis even states that both robust and accurate models …

Classifiers such as deep neural networks have been shown to be vulnerable against
adversarial perturbations on problems with high-dimensional input space. While adversarial …

The goal of this paper is to analyze an intriguing phenomenon recently discovered in deep
networks, that is their instability to adversarial perturbations (Szegedy et al., 2014). We …

We show that there may exist an inherent tension between the goal of adversarial
robustness and that of standard generalization. Specifically, training robust models may not …