保护隐私的多查询问答系统，让大模型安全访问敏感数据。
Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Private
- 用个体隐私过滤机制控制隐私损耗，与查询总数无关。
- 在ε≈10的隐私预算下支持数百次查询，仍保持可用性。
- 适合需要频繁提问且数据敏感的场景，如医疗或金融。
检索增强生成（RAG）通过在推理时从外部语料库中检索文档来提升大语言模型性能。然而，当语料库包含敏感信息时，未经保护的RAG系统可能泄露私密数据。以往工作虽引入差分隐私（DP）保障RAG，但仅限单查询场景，难以满足实际需求。本文研究更贴近现实的多查询设置，提出两种隐私保护的RAG算法：MURAG利用个体隐私过滤机制，使累积隐私损失仅取决于每篇文档被检索的频率，而非总查询数；MURAG-ADA进一步通过私有释放查询特定阈值，实现更精准的相关文档选择。在多个LLM和数据集上的实验表明，所提方法可在ε≈10的实用隐私预算内扩展至数百次查询，同时保持有效性能。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by retrieving documents from an external corpus at inference time. When this corpus contains sensitive information, however, unprotected RAG systems are at risk of leaking private information. Prior work has introduced differential privacy (DP) guarantees for RAG, but only in single-query settings, which fall short of realistic usage. In this paper, we study the more practical multi-query setting and propose two DP-RAG algorithms. The first, MURAG, leverages an individual privacy filter so that the accumulated privacy loss only depends on how frequently each document is retrieved rather than the total number of queries. The second, MURAG-ADA, further improves utility by privately releasing query-specific thresholds, enabling more precise selection of relevant documents. Our experiments across multiple LLMs and datasets demonstrate that the proposed methods scale to hundreds of queries within a practical DP budget ($\varepsilon\approx10$), while preserving meaningful utility.
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。