一作ACL 2026Findings· Findings of ACL
Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment
Zhixue Song · Boyan Han · Yiwei Wang · Chi Zhang
摘要
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...