mlsanityData to 7 Oct 2026

RAG with Differential Privacy

arXiv 2412.19291 ↗First posted 26 Dec 2024cs.LG cs.AI cs.CRcited by 18

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

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) has emerged as the dominant technique to provide Large Language Models (LLM) with fresh and relevant context, mitigating the risk of hallucinations and improving the overall quality of responses in environments with large and fast moving knowledge bases. However, the integration of external documents into the generation process raises significant privacy concerns. Indeed, when added to a prompt, it is not possible to guarantee a response will not inadvertently expose confidential data, leading to potential breaches of privacy and ethical dilemmas. This paper explores a practical solution to this problem suitable to general knowledge extraction from personal data. It shows differentially private token generation is a viable approach to private RAG.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 9 of its 12 references that are in the map. First posted on arXiv 26 Dec 2024.

Builds on

9 of 12 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024DP-RDM: Adapting Diffusion Models to Private Domains Without Fine-Tuning21 Mar
  2. 2024Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems27 Feb

Other references · 7

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2016Deep Learning with Differential Privacycited by 2,682
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  4. 2020Extracting Training Data from Large Language Modelscited by 2,144
  5. 2023How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacycited by 150
  6. 2024Differentially Private Synthetic Data via Foundation Model APIs 2: Textcited by 74
  7. 2022Differentially Private Optimization on Large Model at Small Costcited by 65

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 12.

18 papers.

Sort:

By area:

  1. 2025Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queriescited by 19
  2. 2025Privacy-Aware Decoding: Mitigating Privacy Leakage of Large Language Models in Retrieval-Augmented Generationcited by 8
  3. 2026SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systemscited by 7
  4. 2025Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG)cited by 5
  5. 2025Distributed Retrieval-Augmented Generationcited by 2
  6. 2025Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Privatecited by 2
  7. 2025Privacy Challenges and Solutions in Retrieval-Augmented Generation-Enhanced LLMs for Healthcare Chatbots: A Review of Applications, Risks, and Future Directionscited by 2
  8. 2026Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directionscited by 2
  9. 2026ToolMinimize: Auditing and Rewriting LLM Agent Tool Calls to Minimize Privacy Exposurecited by 1
  10. 2026A Case Study on the Impact of Anonymization Along the RAG Pipelinecited by 0
  11. 2026Adaptive Defense Orchestration for RAG: A Sentinel-Strategist Architecture against Multi-Vector Attackscited by 0
  12. 2026PRAG: End-to-End Privacy-Preserving Retrieval-Augmented Generationcited by 0
6 more
  1. 2026Barriers to Counterfactual Credit Attribution for Autoregressive Modelscited 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. 2026Mitigating Database Leakage in RAG Systems with Keyword-Grounded Fact Substitutioncited by 0
  5. 2026The Privacy-Hallucination Tradeoff in Differentially Private Language Modelscited by 0
  6. 2026Only Pay What You Must Spend: On-Demand Privacy Budget Payment for Differentially Private RAGcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy
  2. 2024The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)
  3. 2026Differentially Private Retrieval-Augmented Generation
  4. 2025Privacy-Aware RAG: Secure and Isolated Knowledge Retrieval
  5. 2024Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation
  6. 2024Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data
  7. 2024Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases
  8. 2025RAG Security and Privacy: Formalizing the Threat Model and Attack Surface