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

• URL: http://arxiv.org/abs/2509.21325v1
• Date: Mon, 01 Sep 2025 07:28:35 GMT
• Title: PIR-RAG: A System for Private Information Retrieval in Retrieval-Augmented Generation
• Authors: Baiqiang Wang, Qian Lou, Mengxin Zheng, Dongfang Zhao,
• Abstract summary: 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.<n>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 protocol.<n>Our work establishes PIR-RAG as a viable and highly efficient solution for privacy in large-scale AI systems.
• Score: 15.952659244056802
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• RAGPulse: An Open-Source RAG Workload Trace to Optimize RAG Serving Systems [10.189392948536446]
  This paper introduces RAGPulse, an open-source RAG workload trace dataset.<n>This dataset was collected from a university-wide Q&A system serving more than 40,000 students and faculties since April 2024.<n>Our analysis reveals that real-world RAG workloads exhibit significant temporal and highly skewed hot document access pattern.
  arXiv  Detail & Related papers  (2025-11-17T05:06:47Z)
• RAGalyst: Automated Human-Aligned Agentic Evaluation for Domain-Specific RAG [0.0]
  Retrieval-Augmented Generation (RAG) is a critical technique for grounding Large Language Models (LLMs) in factual evidence.<n>Existing evaluation frameworks often rely on metrics that fail to capture domain-specific nuances.<n>This paper introduces RAGalyst, an automated, human-aligned agentic framework designed for the rigorous evaluation of domain-specific RAG systems.
  arXiv  Detail & Related papers  (2025-11-06T16:22:52Z)
• Domain-Specific Data Generation Framework for RAG Adaptation [58.20906914537952]
  Retrieval-Augmented Generation (RAG) combines the language understanding and reasoning power of large language models with external retrieval to enable domain-grounded responses.<n>We propose RAGen, a framework for generating domain-grounded question-answer-context (QAC) triples tailored to diverse RAG adaptation approaches.
  arXiv  Detail & Related papers  (2025-10-13T09:59:49Z)
• Versatile and Fast Location-Based Private Information Retrieval with Fully Homomorphic Encryption over the Torus [4.021179028452984]
  We present VeLoPIR, a versatile location-based private information retrieval (PIR) system designed to preserve user privacy.<n>VeLoPIR introduces three operational modes-interval validation, coordinate validation, and identifier matching-that support a broad range of real-world applications.<n>We provide formal security and privacy proofs, confirming the system's robustness under standard cryptographic assumptions.
  arXiv  Detail & Related papers  (2025-06-15T08:01:35Z)
• Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generation [60.81109086640437]
  We propose a novel framework called Federated Retrieval-Augmented Generation (FedE4RAG)<n>FedE4RAG facilitates collaborative training of client-side RAG retrieval models.<n>We apply homomorphic encryption within federated learning to safeguard model parameters.
  arXiv  Detail & Related papers  (2025-04-27T04:26:02Z)
• UltraRAG: A Modular and Automated Toolkit for Adaptive Retrieval-Augmented Generation [64.79921229760332]
  Retrieval-Augmented Generation (RAG) significantly enhances the performance of large language models (LLMs) in downstream tasks.<n>Existing RAG toolkits lack support for knowledge adaptation tailored to specific application scenarios.<n>We propose UltraRAG, a RAG toolkit that automates knowledge adaptation throughout the entire workflow.
  arXiv  Detail & Related papers  (2025-03-31T03:49:49Z)
• MES-RAG: Bringing Multi-modal, Entity-Storage, and Secure Enhancements to RAG [65.0423152595537]
  We propose MES-RAG, which enhances entity-specific query handling and provides accurate, secure, and consistent responses.<n>MES-RAG introduces proactive security measures that ensure system integrity by applying protections prior to data access.<n> Experimental results demonstrate that MES-RAG significantly improves both accuracy and recall, highlighting its effectiveness in advancing the security and utility of question-answering.
  arXiv  Detail & Related papers  (2025-03-17T08:09:42Z)
• A Comprehensive Survey on Composed Image Retrieval [54.54527281731775]
  Composed Image Retrieval (CIR) is an emerging yet challenging task that allows users to search for target images using a multimodal query.<n>There is currently no comprehensive review of CIR to provide a timely overview of this field.<n>We synthesize insights from over 120 publications in top conferences and journals, including ACM TOIS, SIGIR, and CVPR.
  arXiv  Detail & Related papers  (2025-02-19T01:37:24Z)
• Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMs [67.0310240737424]
  We introduce a novel approach to safeguard the ownership of text datasets and effectively detect unauthorized use by the RA-LLMs.<n>Our approach preserves the original data completely unchanged while protecting it by inserting specifically designed canary documents into the IP dataset.<n>During the detection process, unauthorized usage is identified by querying the canary documents and analyzing the responses of RA-LLMs.
  arXiv  Detail & Related papers  (2025-02-15T04:56:45Z)
• C-FedRAG: A Confidential Federated Retrieval-Augmented Generation System [7.385458207094507]
  We introduce Confidential Computing (CC) techniques as a solution for secure Federated Retrieval Augmented Generation (FedRAG)<n>Our proposed Confidential FedRAG system (C-FedRAG) enables secure connection and scaling of a RAG across a decentralized network of data providers by ensuring context confidentiality.
  arXiv  Detail & Related papers  (2024-12-17T18:42:21Z)
• FastRAG: Retrieval Augmented Generation for Semi-structured Data [1.4249472316161877]
  This paper introduces FastRAG, a novel RAG approach designed for semi-structured data.<n>FastRAG employs schema learning and script learning to extract and structure data without needing to submit entire data sources to an LLM.<n>It integrates text search with knowledge graph querying to improve accuracy in retrieving context-rich information.
  arXiv  Detail & Related papers  (2024-11-21T01:00:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.