Detecting Adversarial Images through Response Profiles of Vision-Language Models

Paper recorded by Signals 4 on 2026-10-07 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-07 on arXiv · recorded by Signals 4 on 2026-10-08

Category: cs.CV · 计算机视觉 · first seen 2026-10-08

Abstract

Adversarial perturbations can alter the predictions of frozen vision-language models (VLMs) while leaving their confidence and image--text similarity patterns seemingly plausible. We investigate whether we can identify adversarial inputs based on the broader way an image interacts with a collection of general semantic prompts. Our detector summarizes these responses using category-level statistics

Read on arXiv →