THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models 文章

ArXiv CS.CL2026-06-02NEWSen作者: Zhiqing Ma, Zhonghao Xu, Dong Yu, Chen Kang, Changliang Li, Pengyuan Liu
查看原文 →
关系图谱

THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models · 相关技术

相关技术

LLM