mlsanityData to 14 Oct 2026

RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service

arXiv 2412.12775 ↗First posted 17 Dec 2024cs.IR cs.CRcited by 17

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

Abstract (arXiv)

Retrieval-augmented generation (RAG) improves the service quality of large language models by retrieving relevant documents from credible literature and integrating them into the context of the user query. Recently, the rise of the cloud RAG service has made it possible for users to query relevant documents conveniently. However, directly sending queries to the cloud brings potential privacy leakage. In this paper, we are the first to formally define the privacy-preserving cloud RAG service to protect the user query and propose RemoteRAG as a solution regarding privacy, efficiency, and accuracy. For privacy, we introduce (n,ε)-DistanceDP to characterize privacy leakage of the user query and the leakage inferred from relevant documents. For efficiency, we limit the search range from the total documents to a small number of selected documents related to a perturbed embedding generated from (n,ε)-DistanceDP, so that computation and communication costs required for privacy protection significantly decrease. For accuracy, we ensure that the small range includes target documents related to the user query with detailed theoretical analysis. Experimental results also demonstrate that RemoteRAG can resist existing embedding inversion attack methods while achieving no loss in retrieval under various settings. Moreover, RemoteRAG is efficient, incurring only 0.67 seconds and 46.66KB of data transmission (2.72 hours and 1.43 GB with the non-optimized privacy-preserving scheme) when retrieving from a total of 106 documents.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 18 of its 45 references that are in the map. First posted on arXiv 17 Dec 2024.

Builds on

18 of 45 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy6 Dec
  2. 2024The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)23 Feb

Other references · 16

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
  4. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  5. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  6. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  7. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  8. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 192
  9. 2023LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examplescited by 177
  10. 2023Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generationcited by 96
  11. 2023Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspectivecited by 92
  12. 2023Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentencecited by 81
4 more
  1. 2023DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineercited by 57
  2. 2023Hide and Seek (HaS): A Lightweight Framework for Prompt Privacy Protectioncited by 38
  3. 2023Protecting User Privacy in Remote Conversational Systems: A Privacy-Preserving framework based on text sanitizationcited by 23
  4. 2024Understanding and Mitigating the Threat of Vec2Text to Dense Retrieval Systemscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 14.

17 papers.

Sort:

By area:

  1. 2025A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthinesscited by 7
  2. 2025Exposing Privacy Risks in Graph Retrieval-Augmented Generationcited by 5
  3. 2026Efficient Privacy-Preserving Retrieval Augmented Generation with Distance-Preserving Encryptioncited by 4
  4. 2025Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Privatecited by 3
  5. 2026Making Theft Useless: Adulteration-Based Protection of Proprietary Knowledge Graphs in GraphRAG Systemscited by 2
  6. 2026Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directionscited by 2
  7. 2026Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddingscited by 2
  8. 2026P2RAG: Efficient Privacy-Preserving RAG Service Supporting Arbitrary Top-k Retrievalcited by 1
  9. 2026Opal: Private Memory for Personal AIcited by 1
  10. 2026Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scalecited by 1
  11. 2026A Case Study on the Impact of Anonymization Along the RAG Pipelinecited by 0
  12. 2026PRAG: End-to-End Privacy-Preserving Retrieval-Augmented Generationcited by 0
5 more
  1. 2026Auditing Privacy in Multi-Tenant RAG under Account Collusioncited by 0
  2. 2026Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systemscited by 0
  3. 2026Is External Database Protection Static in Retrieval-Augmented Generation? Rethinking Privacy Preservation under Dynamic Queriescited by 0
  4. 2026Retrieval-Augmented Large Language Models as Components of Cognitive Computing architecture for Regulatory Knowledge Managementcited by 0
  5. 2026Mitigating Database Leakage in RAG Systems with Keyword-Grounded Fact Substitutioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Privacy-Aware RAG: Secure and Isolated Knowledge Retrieval
  2. 2025Privacy-Preserving LLM Embedding Transmission for End-Cloud Collaboration
  3. 2025Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG)
  4. 2025Privacy-Preserving Federated Embedding Learning for Localized Retrieval-Augmented Generation
  5. 2025PIR-RAG: A System for Private Information Retrieval in Retrieval-Augmented Generation
  6. 2024Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases
  7. 2026PILLAR: Private Inverted-Index Lexical Lookup for Augmented Retrieval
  8. 2025Safeguarding Privacy of Retrieval Data against Membership Inference Attacks: Is This Query Too Close to Home?