Jun 2026
A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP
This work proposes $A^4D$ Attack- and Architecture-Agnostic Adversarial Detector, a completely black-box, zero-shot adversarial attack detection framework that utilizes prompt-based similarity scores derived from CLIP, the first attempt to utilize CLIP for such a task.
Hodaya Krakover, M. Levi, Eyal Gofer et al.
· arXiv.org · 0 citations