P$^2$RAG: 支持任意Top-$k$检索的高效隐私保护RAG服务
P$^2$RAG: Efficient Privacy-Preserving RAG Service Supporting Arbitrary Top-$k$ Retrieval
AI总结：
针对现有隐私保护RAG系统无法灵活支持大k值且效率低下的问题，提出基于秘密共享和交互式二分法的P$^2$RAG系统，避免排序开销，实现高效且安全的任意top-$k$检索。
摘要：
检索增强生成（RAG）使大型语言模型能够利用外部知识，但外包RAG服务会引发数据所有者和用户的隐私担忧。隐私保护RAG系统通过执行安全的top-$k$检索来解决这些问题，通常使用安全排序来识别相关文档。然而，现有系统面临支持任意$k$的挑战，因为它们无法更改$k$，存在新的安全问题，尤其是当$k$较大时效率下降。这是一个重大限制，因为金融、法律和医疗等应用需要足够大的$k$，导致现有系统开销巨大。此外，现代长上下文模型通常通过更大的检索集获得更高的准确性。我们提出P$^2$RAG，一种高效隐私保护的RAG服务，支持任意top-$k$检索。与现有系统不同，P$^2$RAG避免对候选文档进行排序，而是使用交互式二分法来确定top-$k$文档集。在安全性方面，P$^2$RAG在两个半诚实非共谋服务器上使用秘密共享来保护数据所有者的数据库和用户的提示。它通过限制和验证来防御恶意用户，并严格限制数据库的信息泄露。实验表明，对于$k = 16$--$1024$，P$^2$RAG比最先进的PRAG快3--300倍。
英文摘要：
Retrieval-Augmented Generation (RAG) enables large language models to use external knowledge, but outsourcing the RAG service raises privacy concerns for both data owners and users. Privacy-preserving RAG systems address these concerns by performing secure top-$k$ retrieval, which is typically implemented using secure sorting to identify relevant documents. However, existing systems face challenges supporting arbitrary $k$ due to their inability to change $k$, new security issues, and in particular, efficiency degradation with large $k$. This is a significant limitation because applications such as finance, law, and healthcare require a $k$ that is large enough to cause huge overhead for existing systems. Also, modern long-context models generally achieve higher accuracy with larger retrieval sets. We propose P$^2$RAG, an efficient privacy-preserving RAG service that supports arbitrary top-$k$ retrieval. Unlike existing systems, P$^2$RAG avoids sorting candidate documents. Instead, it uses an interactive bisection method to determine the set of top-$k$ documents. For security, P$^2$RAG uses secret sharing on two semi-honest non-colluding servers to protect the data owner's database and the user's prompt. It enforces restrictions and verification to defend against malicious users and tightly bounds the information leakage of the database. The experiments show that P$^2$RAG is 3--300$\times$ faster than the state-of-the-art PRAG for $k = 16$--$1024$.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
