用可学习的哈希短列表实现高效私密密集检索，兼顾安全与精度。
Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale
- 用随机二进制编码生成候选文档短列表，缩小搜索范围。
- 200-500个候选项即可接近全库检索效果，268万段落仅增0.73秒延迟。
- 适合对隐私敏感且需高精度的规模化检索场景。
托管检索增强生成（RAG）和语义搜索使用户能够查询提供商持有的宝贵语料库，但面临两个矛盾需求：隐藏每个查询和选定结果，同时仅披露用户有权限访问的文档。现有加密方法要么因处理整个语料库而代价高昂，要么为追求效率牺牲质量，仅扫描少量聚类。本文重新利用学习得到的深度哈希作为私密过滤器：随机二进制码将服务商指向一个简短候选列表，结合加密重排序与无感知密钥传输，保护精确查询和最终选择。该短列表绕过全库加密搜索，不损失检索质量——在五个零样本语料库（覆盖2.5万至540万文档）上，200–500个候选项已能紧密匹配全库检索表现。在包含268万段落的NQ语料库上，通过10 Gbps链路运行时，本协议仅使128词元的Qwen3-32B RAG流水线增加0.73秒（即10%）。发布的代码满足方向性度量差分隐私（DP），显著降低嵌入反演和属性推断泄露风险，证明精心学习的短列表可让私密密集检索既准确又实用。
原文摘要 · Abstract (English)
Hosted retrieval-augmented generation (RAG) and semantic search allow users to query valuable provider-held corpora, raising two competing demands: to hide each query and chosen result, yet reveal only the documents that the user is authorized to receive. Existing cryptographic approaches either make this costly by processing the entire corpus for every query, or sacrifice quality for efficiency by scanning a few clusters. We repurpose learned deep hashing as a private filter: a randomized binary code points the provider to a short candidate list, while encrypted reranking and oblivious key transfer protect the precise query and final selection. This shortlist short-circuits full-corpus cryptographic search without sacrificing retrieval quality: with 200-500 candidates, it closely matches full-corpus retrieval across five zero-shot corpora spanning 25K to 5.4M documents. On the full 2.68M-passage NQ corpus over a 10-Gbps link, our protocol only adds 0.73 seconds, or 10 percent, to a 128-token Qwen3-32B RAG pipeline. The released code satisfies directional metric differential privacy (DP) and substantially reduces embedding-inversion and property-inference leakage, demonstrating that a carefully learned shortlist can make private dense retrieval both accurate and practical.
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。