Abstract: Vision Transformers (ViTs) have achieved remarkable performance in computer vision tasks but are vulnerable to adversarial attacks. Recent studies have demonstrated the feasibility of ...

Adversarial Machine Learning sits at the intersection of mathematics and security. It's fundamentally different from prompt injection or jailbreaking because these attacks exploit the mathematical ...

ViT models are all available in timm library. We consider four surrogate models (vit_base_patch16_224, pit_b_224, cait_s24_224, and visformer_small) and four additional target models ...