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 …

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 …

We identify a trade-off between robustness and accuracy that serves as a guiding principle
in the design of defenses against adversarial examples. Although this problem has been …

Adversarial training (AT) is currently one of the most successful methods to obtain the
adversarial robustness of deep neural networks. However, the phenomenon of robust …

Adversarial examples cause neural networks to produce incorrect outputs with high
confidence. Although adversarial training is one of the most effective forms of defense …

Adversarial robustness has emerged as an important topic in deep learning as carefully
crafted attack samples can significantly disturb the performance of a model. Many recent …

Deep neural networks are susceptible to adversarial examples, posing a significant security
risk in critical applications. Adversarial Training (AT) is a well-established technique to …

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 has been widely acknowledged as the most effective method to improve
the adversarial robustness against adversarial examples for Deep Neural Networks (DNNs) …

The last six years have witnessed significant progress in adversarially robust deep learning.
As evidenced by the CIFAR-10 dataset category in RobustBench benchmark, the accuracy …