SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts 文章

ArXiv CS.CL2026-05-29NEWSen作者: Yuan Xin, Yixuan Weng, Minjun Zhu, Ying Ling, Chengwei Qin, Michael Backes, Yue Zhang, Linyi Yang
AI 安全
查看原文 →
关系图谱

SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts · 相关技术

相关技术

prompt injectionadversarial trainingadversarial hidden promptslarge language models