Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization 事件

Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization arXiv:2605.10764v2 Announce Type: replace Abstract: Recent studies show that gradient-based universal image jailbreaks on vision-language models (VLMs) exhibit little or no cross-model transferability, casting doubt on the feasibility of transferable multimodal jailbreaks. We revisit this conclusion under a strictly untargeted threat model without enforcing a fixed prefix or response pattern. Our preliminary experimen