Skip to content
arXiv cs.CV · Papers

Adversarial Decoys: Misdirecting Attention-Based Defenses in ViT

arXiv:2607.07922v1 Announce Type: new Abstract: Vision Transformers (ViTs) remain vulnerable to localized adversarial attacks, e.g., adversarial patches, while recent test-time defenses mitigate them by suppressing image tokens with abnormally high attention scores. These defenses exploit a strong coupling between atte