In adversarial machine learning, deep neural networks can fit the adversarial examples on
the training dataset but have poor generalization ability on the test set. This phenomenon is …

Adversarial training has become the de-facto standard method for improving the robustness
of models against adversarial examples. However, robust overfitting remains a significant …

Deep neural networks have achieved remarkable results across various tasks. However,
they are susceptible to adversarial examples, which are generated by adding adversarial …

Fast adversarial training (FAT) is beneficial for improving the adversarial robustness of
neural networks. However, previous FAT work has encountered a significant issue known as …

Single-step adversarial training (SSAT) has demonstrated the potential to achieve both
efficiency and robustness. However, SSAT suffers from catastrophic overfitting (CO), a …

Overfitting negatively impacts the generalization ability of deep neural networks (DNNs) in
both natural and adversarial training. Existing methods struggle to consistently address …

Numerous studies have demonstrated the susceptibility of deep neural networks (DNNs) to
subtle adversarial perturbations prompting the development of many advanced adversarial …

The neural network model has the drawback of making incorrect predictions under the
influence of slight adversarial perturbations. Single-step adversarial training (AT) is an …

While adversarial training methods have resulted in significant improvements in the deep
neural nets' robustness against norm-bounded adversarial perturbations, their …

Adversarial training has achieved remarkable advancements in defending against
adversarial attacks. Among them, fast adversarial training (FAT) is gaining attention for its …