AIBearisharXiv – CS AI · 6h ago7/10
🧠
Conceal, Reconstruct, Jailbreak: Exploiting the Reconstruction-Concealment Tradeoff in MLLMs
Researchers have identified a fundamental vulnerability in multimodal large language models where safety mechanisms can be bypassed by exploiting the tension between hiding harmful intent and maintaining reconstructability. The study demonstrates that character-removed text variants combined with keyword-related distractor images achieve effective jailbreaks, revealing that models' own reconstruction capabilities become a security liability.