提出检测并隐藏敏感检索数据，保护RAG系统隐私
Safeguarding Privacy of Retrieval Data against Membership Inference Attacks: Is This Query Too Close to Home?
- 基于查询与目标文档的高相似性特征，设计新型隐私检测框架
- 可有效防御多种先进成员推断攻击，且不降低数据可用性
- 适用于现有RAG系统，无需修改架构，适合注重隐私的应用
检索增强生成（RAG）能缓解大语言模型的幻觉问题，并在个性化应用中表现良好。然而，直接将私有检索文档传给大模型会引发成员推断攻击（MIA），攻击者试图判断目标数据是否存在于私有外部数据库中。基于MIA查询通常仅与一个目标文档高度相似的观察，本文提出一种面向RAG系统的新型基于相似性的MIA检测框架。利用该方法，我们证明了一种简单的‘检测-隐藏’策略可成功混淆攻击者，同时保持数据效用和系统无关性。实验验证了其对多种前沿MIA方法的有效检测与防御能力，并展示了其在现有RAG系统中的良好适应性。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) mitigates the hallucination problem in large language models (LLMs) and has proven effective for personalized usages. However, delivering private retrieved documents directly to LLMs introduces vulnerability to membership inference attacks (MIAs), which try to determine whether the target data point exists in the private external database or not. Based on the insight that MIA queries typically exhibit high similarity to only one target document, we introduce a novel similarity-based MIA detection framework designed for the RAG system. With the proposed method, we show that a simple detect-and-hide strategy can successfully obfuscate attackers, maintain data utility, and remain system-agnostic against MIA. We experimentally prove its detection and defense against various state-of-the-art MIA methods and its adaptability to existing RAG systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。