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 …

Abstract Vision Transformer (ViT), as a powerful alternative to Convolutional Neural Network
(CNN), has received much attention. Recent work showed that ViTs are also vulnerable to …

Single-step adversarial training (AT) has received wide attention as it proved to be both
efficient and robust. However, a serious problem of catastrophic overfitting exists, ie, the …

Fast adversarial training (FAT) effectively improves the efficiency of standard adversarial
training (SAT). However, initial FAT encounters catastrophic overfitting, ie, the robust …

Abstract Recently, Wong et al.(2020) showed that adversarial training with single-step FGSM
leads to a characteristic failure mode named catastrophic overfitting (CO), in which a model …

Adversarial training (AT) has been demonstrated to be effective in improving model
robustness by leveraging adversarial examples for training. However, most AT methods are …

In recent years, researches on adversarial attacks and defense mechanisms have obtained
much attention. It's observed that adversarial examples crafted with small malicious …

Adversarial training is widely used to improve the robustness of deep neural networks to
adversarial attack. However, adversarial training is prone to overfitting, and the cause is far …

Although current deep learning techniques have yielded superior performance on various
computer vision tasks, yet they are still vulnerable to adversarial examples. Adversarial …