AIBullisharXiv – CS AI · 9h ago7/10
🧠
Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs
Researchers propose SAEgis, a lightweight adversarial attack detection framework using sparse autoencoders (SAEs) to protect vision-language models from adversarial perturbations. The plug-and-play method requires no additional adversarial training and demonstrates strong cross-domain generalization, addressing a critical safety gap in increasingly deployed VLM systems.