Few Tokens Matter Vlm Attacks

Demonstrate that adversarial attacks on vision-language models need not target all tokens equally. Entropy-guided attacks identify high-entropy tokens (critical decision points) where perturbations have maximum impact, achieving comparable attack success with 80% fewer tokens targeted.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 2f1b1b502a

Frequently asked questions

npx get-skill add adu2021/few-tokens-matter-vlm-attacks