AI RESEARCH
Benign Overfitting in Adversarial Training for Vision Transformers
arXiv CS.AI
•
ArXi:2604.19724v1 Announce Type: cross Despite the remarkable success of Vision Transformers (ViTs) across a wide range of vision tasks, recent studies have revealed that they remain vulnerable to adversarial examples, much like Convolutional Neural Networks (CNNs). A common empirical defense strategy is adversarial