PIR-RAG: A System for Private Information Retrieval in Retrieval-Augmented Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Baiqiang, Lou, Qian, Zheng, Mengxin, Zhao, Dongfang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909806477967360
author Wang, Baiqiang
Lou, Qian
Zheng, Mengxin
Zhao, Dongfang
author_facet Wang, Baiqiang
Lou, Qian
Zheng, Mengxin
Zhao, Dongfang
contents Retrieval-Augmented Generation (RAG) has become a foundational component of modern AI systems, yet it introduces significant privacy risks by exposing user queries to service providers. To address this, we introduce PIR-RAG, a practical system for privacy-preserving RAG. PIR-RAG employs a novel architecture that uses coarse-grained semantic clustering to prune the search space, combined with a fast, lattice-based Private Information Retrieval (PIR) protocol. This design allows for the efficient retrieval of entire document clusters, uniquely optimizing for the end-to-end RAG workflow where full document content is required. Our comprehensive evaluation against strong baseline architectures, including graph-based PIR and Tiptoe-style private scoring, demonstrates PIR-RAG's scalability and its superior performance in terms of "RAG-Ready Latency"-the true end-to-end time required to securely fetch content for an LLM. Our work establishes PIR-RAG as a viable and highly efficient solution for privacy in large-scale AI systems.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21325
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PIR-RAG: A System for Private Information Retrieval in Retrieval-Augmented Generation
Wang, Baiqiang
Lou, Qian
Zheng, Mengxin
Zhao, Dongfang
Information Retrieval
Artificial Intelligence
Cryptography and Security
Retrieval-Augmented Generation (RAG) has become a foundational component of modern AI systems, yet it introduces significant privacy risks by exposing user queries to service providers. To address this, we introduce PIR-RAG, a practical system for privacy-preserving RAG. PIR-RAG employs a novel architecture that uses coarse-grained semantic clustering to prune the search space, combined with a fast, lattice-based Private Information Retrieval (PIR) protocol. This design allows for the efficient retrieval of entire document clusters, uniquely optimizing for the end-to-end RAG workflow where full document content is required. Our comprehensive evaluation against strong baseline architectures, including graph-based PIR and Tiptoe-style private scoring, demonstrates PIR-RAG's scalability and its superior performance in terms of "RAG-Ready Latency"-the true end-to-end time required to securely fetch content for an LLM. Our work establishes PIR-RAG as a viable and highly efficient solution for privacy in large-scale AI systems.
title PIR-RAG: A System for Private Information Retrieval in Retrieval-Augmented Generation
topic Information Retrieval
Artificial Intelligence
Cryptography and Security
url https://arxiv.org/abs/2509.21325