AI RESEARCH
Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment
arXiv CS.AI
•
ArXi:2605.07250v1 Announce Type: cross Recent advancements in visual context compression enable MLLMs to process ultra-long contexts efficiently by rendering text into images. However, we identify a critical vulnerability inherent to this paradigm: lowering image resolution inadvertently catalyzes jailbreaking. Our experiments reveal that the safety defenses of SOTA models deteriorate sharply as resolution degrades, surprisingly persisting even when text remains legible.