1
Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces
最新研究发现，通过模拟审核轨迹可绕过函数调用LLM的安全限制，揭示大模型越狱攻击新路径。
arXiv:2607.00481v1 Announce Type: cross Abstract: Jailbreak attacks remain a critical threat to the safe deployment of large language models (LLMs). W…