Early stopping methods in deep learning face the challenge of balancing the volume of
training and validation data, especially in the presence of label noise. Concretely, sparing …

Although pre-trained models such as Contrastive Language-Image Pre-Training (CLIP)
show impressive generalization results, their robustness is still limited under Out-of …

Abstract Out-of-Distribution (OOD) Generalization aims to learn robust models that
generalize well to various environments without fitting to distribution-specific features …

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

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 …

Catastrophic overfitting (CO) presents a significant challenge in single-step adversarial
training (AT), manifesting as highly distorted deep neural networks (DNNs) that are …

Deep neural networks (DNNs) have achieved remarkable success across various fields but
remain highly vulnerable to adversarial attacks, prompting the development of numerous …

The widespread adoption of deep neural networks (DNNs) has raised significant concerns
about their robustness, particularly in real-world environments characterized by inherent …