mlsanityData to 7 Oct 2026

PRAG: End-to-End Privacy-Preserving Retrieval-Augmented Generation

arXiv 2604.26525 ↗First posted 29 Apr 2026cs.CRcited by 0

On the map: Retrieval-augmented generation → Privacy and security of RAG

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) is essential for enhancing Large Language Models (LLMs) with external knowledge, but its reliance on cloud environments exposes sensitive data to privacy risks. Existing privacy-preserving solutions often sacrifice retrieval quality due to noise injection or only provide partial encryption. We propose PRAG, an end-to-end privacy-preserving RAG system that achieves end-to-end confidentiality for both documents and queries without sacrificing the scalability of cloud-hosted RAG. PRAG features a dual-mode architecture: a non-interactive PRAG-I utilizes homomorphic-friendly approximations for low-latency retrieval, while an interactive PRAG-II leverages client assistance to match the accuracy of non-private RAG. To ensure robust semantic ordering, we introduce Operation-Error Estimation (OEE), a mechanism that stabilizes ranking against homomorphic noise. Experiments on large-scale datasets demonstrate that PRAG achieves competitive recall (72.45%-74.45%), practical retrieval latency, and strong resilience against graph reconstruction attacks while maintaining end-to-end confidentiality. This work confirms the feasibility of secure, high-performance RAG at scale.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 17 of its 53 references that are in the map. First posted on arXiv 29 Apr 2026.

Builds on

17 of 53 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025Privacy-Aware RAG: Secure and Isolated Knowledge Retrieval17 Mar
  2. 2024RAG with Differential Privacy26 Dec
  3. 2024RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service17 Dec
  4. 2024Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy6 Dec
  5. 2024FRAG: Toward Federated Vector Database Management for Collaborative and Secure Retrieval-Augmented Generation17 Oct
  6. 2024The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)23 Feb

Other references · 11

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  3. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  4. 2024In Defense of RAG in the Era of Long-Context Language Modelscited by 52
  5. 2023Privacy Implications of Retrieval-Based Language Modelscited by 31
  6. 2019SANNS: Scaling Up Secure Approximate k-Nearest Neighbors Searchcited by 12
  7. 2024SOAR: Improved Indexing for Approximate Nearest Neighbor Searchcited by 12
  8. 2024Fortify Your Foundations: Practical Privacy and Security for Foundation Model Deployments In The Cloudcited by 4
  9. 2023A Highly Accurate Query-Recovery Attack against Searchable Encryption using Non-Indexed Documentscited by 2
  10. 2017Efficient Dynamic Searchable Encryption with Forward Privacycited by 1
  11. 2021IHOP: Improved Statistical Query Recovery against Searchable Symmetric Encryption through Quadratic Optimizationcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026P2RAG: Efficient Privacy-Preserving RAG Service Supporting Arbitrary Top-k Retrieval
  2. 2025Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Private
  3. 2026Efficient Privacy-Preserving Retrieval Augmented Generation with Distance-Preserving Encryption
  4. 2025Privacy-Aware Decoding: Mitigating Privacy Leakage of Large Language Models in Retrieval-Augmented Generation
  5. 2026GoldenRetriever: Non-Interactive Homomorphic Encrypted Retrieval for Privacy-Preserving RAG
  6. 2026Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems
  7. 2024Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data
  8. 2025PIR-RAG: A System for Private Information Retrieval in Retrieval-Augmented Generation