Mind the Hook: Source-Level Auditing of Privacy Defenses in Retrieval-Augmented Generation
注意钩子:检索增强生成中隐私防御的源级审计
专题命中 检索器与排序 :RAG(summary_cn,abstract);retrieval-augmented generation(title,abstract)
AI总结 该研究针对RAG的黑盒隐私分数解读难题,提出活跃路径审计方法,通过梳理源级钩子、映射泄漏通道、金丝雀验证,复现分析DP与LPRAG防御的隐私效果,贡献方法论与案例研究。
Comments 6 pages, 1 figure. Accepted as a regular paper at the 25th IEEE International Conference on Machine Learning and Applications (ICMLA 2026)