1
D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output Rewriting
用输出重写破坏多轮越狱攻击，语义保持下高效防御，AI安全新方法。
arXiv:2606.02640v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks pose a growing threat to large language model (LLM) safety because they…