AIBullisharXiv – CS AI · Feb 277/105
🧠
Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP
Researchers developed Dyslexify, a training-free defense mechanism against typographic attacks on CLIP vision models that inject malicious text into images. The method selectively disables attention heads responsible for text processing, improving robustness by up to 22% while maintaining 99% of standard performance.