Adversarial training is one of the most effective approaches defending against adversarial
examples for deep learning models. Unlike other defense strategies, adversarial training …

Deep neural networks are exposed to the risk of adversarial attacks via the fast gradient sign
method (FGSM), projected gradient descent (PGD) attacks, and other attack algorithms …

The field of defense strategies against adversarial attacks has significantly grown over the
last years, but progress is hampered as the evaluation of adversarial defenses is often …

Cross-entropy is a widely used loss function in applications. It coincides with the logistic loss
applied to the outputs of a neural network, when the softmax is used. But, what guarantees …

As a research community, we are still lacking a systematic understanding of the progress on
adversarial robustness which often makes it hard to identify the most promising ideas in …

Adversarial training suffers from robust overfitting, a phenomenon where the robust test
accuracy starts to decrease during training. In this paper, we focus on reducing robust …

The study on improving the robustness of deep neural networks against adversarial
examples grows rapidly in recent years. Among them, adversarial training is the most …

Adversarial training and its variants have become de facto standards for learning robust
deep neural networks. In this paper, we explore the landscape around adversarial training in …

Adversarial training, which minimizes the maximal risk for label-preserving input
perturbations, has proved to be effective for improving the generalization of language …

A recent line of work focused on making adversarial training computationally efficient for
deep learning models. In particular, Wong et al.(2020) showed that $\ell_\infty $-adversarial …