Adversarial training (AT) has become an effective defense method against adversarial
examples (AEs) and it is typically framed as a bi-level optimization problem. Among various …

Abstract Fast Adversarial Training (FAT) has gained increasing attention within the research
community owing to its efficacy in improving adversarial robustness. Particularly noteworthy …

Adversarial training (AT) refers to integrating adversarial examples--inputs altered with
imperceptible perturbations that can significantly impact model predictions--into the training …

It has been widely substantiated that deep neural networks (DNNs) are susceptible and
vulnerable to adversarial perturbations. Existing studies mainly focus on performing attacks …

Catastrophic overfitting (CO) poses a significant challenge to fast adversarial training
(FastAT), particularly at large perturbation scales, leading to dramatic reductions in …

In this paper, we explore the latent distribution of adversarial examples in terms of the angle
between the adversarial perturbation and the image manifold to optimize adversarial …

With the wide application of deep neural network models in various computer vision tasks,
there has been a proliferation of adversarial example generation strategies aimed at deeply …

Adversarial training has become a primary method for enhancing the robustness of deep
learning models. In recent years, fast adversarial training methods have gained widespread …

While adversarial training is an effective defense method against adversarial attacks, it
notably increases the training cost. To this end, fast adversarial training (FAT) is presented …

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