MARS steers multimodal safety from textual refusal directions
The training-free method was tested on five state-of-the-art MLLMs for safety, utility, and video jailbreaks.
Stories per day · 30 days
2 RSS
2 stories, newest first · one card per story
Stories tagged #multimodal-safety
Do Input-Level Defenses Transfer to Observation-Level Attacks on VideoLLMs?
A systematic study shows input-level adversarial defenses provide inconsistent, often near-zero protection against observation-level attacks on video LLMs.