Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation
可检索但不可靠:检索增强生成中的攻击与防御研究综述
AI总结 本综述针对检索增强生成(RAG)的安全与鲁棒性问题,形式化其各阶段威胁模型,分类攻击目标并梳理各阶段防御及评估方法,为该领域提供统一研究框架。
Comments 24 pages, 6 figures. Accepted to Findings of the Association for Computational Linguistics: EMNLP 2026. Peer-reviewed through ACL Rolling Review (ARR)