Robust overfitting widely exists in adversarial training of deep networks. The exact
underlying reasons for this are still not completely understood. Here, we explore the causes …

Backdoor defense, which aims to detect or mitigate the effect of malicious triggers introduced
by attackers, is becoming increasingly critical for machine learning security and integrity …

Adversarial phenomenon has been widely observed in machine learning (ML) systems,
especially in those using deep neural networks, describing that ML systems may produce …

Adversarial Training (AT), which adversarially perturb the input samples during training, has
been acknowledged as one of the most effective defenses against adversarial attacks, yet …

Sharpness-Aware Minimization (SAM) is an effective method for improving generalization
ability by regularizing loss sharpness. In this paper, we explore SAM in the context of …

Personalized federated learning, as a variant of federated learning, trains customized
models for clients using their heterogeneously distributed data. However, it is still …

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 …

Adversarial training (AT) is currently one of the most effective ways to obtain the robustness
of deep neural networks against adversarial attacks. However most AT methods suffer from …

Deep neural networks are vulnerable to adversarial examples. Adversarial training (AT) is
an effective defense against adversarial examples. However, AT is prone to overfitting which …