3 papers
cs.CV2025
The Power of Many: Synergistic Unification of Diverse Augmentations for Efficient Adversarial Robustness
Wang Yu-Hang, Shiwei Li, Jianxiang Liao +3
Adversarial perturbations pose a significant threat to deep learning models. Adversarial Training (AT), the predominant defense method, faces challenges of high computational costs…
cs.LG2025
Ignition Phase : Standard Training for Fast Adversarial Robustness
Wang Yu-Hang, Liu ying, Fang liang +6
Adversarial Training (AT) is a cornerstone defense, but many variants overlook foundational feature representations by primarily focusing on stronger attack generation. We introduc…
cs.LG2025
TAET: Two-Stage Adversarial Equalization Training on Long-Tailed Distributions
Wang YuHang, Junkang Guo, Aolei Liu +5
Adversarial robustness is a critical challenge in deploying deep neural networks for real-world applications. While adversarial training is a widely recognized defense strategy, mo…