mlsanityData to 7 Oct 2026

Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data

arXiv 2406.14773 ↗First posted 20 Jun 2024cs.CRcited by 52

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

Abstract (arXiv)

Retrieval-augmented generation (RAG) enhances the outputs of language models by integrating relevant information retrieved from external knowledge sources. However, when the retrieval process involves private data, RAG systems may face severe privacy risks, potentially leading to the leakage of sensitive information. To address this issue, we propose using synthetic data as a privacy-preserving alternative for the retrieval data. We propose SAGE, a novel two-stage synthetic data generation paradigm. In the stage-1, we employ an attribute-based extraction and generation approach to preserve key contextual information from the original data. In the stage-2, we further enhance the privacy properties of the synthetic data through an agent-based iterative refinement process. Extensive experiments demonstrate that using our synthetic data as the retrieval context achieves comparable performance to using the original data while substantially reducing privacy risks. Our work takes the first step towards investigating the possibility of generating high-utility and privacy-preserving synthetic data for RAG, opening up new opportunities for the safe application of RAG systems in various domains.

Key facts. Cited by 52 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 21 of its 40 references that are in the map. First posted on arXiv 20 Jun 2024.

Builds on

21 of 40 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems27 Feb
  2. 2024The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)23 Feb

Other references · 19

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  3. 2020Extracting Training Data from Large Language Modelscited by 2,144
  4. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 788
  5. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  6. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  7. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  8. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 343
  9. 2023Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Biascited by 230
  10. 2022ZeroGen: Efficient Zero-shot Learning via Dataset Generationcited by 209
  11. 2022Generating Training Data with Language Models: Towards Zero-Shot Language Understandingcited by 199
  12. 2022What Does it Mean for a Language Model to Preserve Privacy?cited by 194
7 more
  1. 2021Retrieval Augmented Code Generation and Summarizationcited by 148
  2. 2023Lift Yourself Up: Retrieval-augmented Text Generation with Self Memorycited by 103
  3. 2023Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generationcited by 94
  4. 2024Differentially Private Synthetic Data via Foundation Model APIs 2: Textcited by 74
  5. 2024Copyright Protection in Generative AI: A Technical Perspectivecited by 35
  6. 2023A Linear Reconstruction Approach for Attribute Inference Attacks against Synthetic Datacited by 23
  7. 2023Mixture of Soft Prompts for Controllable Data Generationcited by 23

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 22; 2026: 25.

52 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  2. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Surveycited by 83
  3. 2024Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agentscited by 63
  4. 2024Privacy-Preserving Retrieval-Augmented Generation with Differential Privacycited by 38
  5. 2025Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Surveycited by 29
  6. 2024Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generationcited by 25
  7. 2025Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queriescited by 19
  8. 2025Security of Internet of Agents: Attacks and Countermeasurescited by 17
  9. 2025A False Sense of Privacy: Evaluating Textual Data Sanitization Beyond Surface-level Privacy Leakagecited by 15
  10. 2025EnronQA: Towards Personalized RAG over Private Documentscited by 8
  11. 2025Privacy-Aware Decoding: Mitigating Privacy Leakage of Large Language Models in Retrieval-Augmented Generationcited by 8
  12. 2026SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systemscited by 7
38 more
  1. 2026MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agentscited by 7
  2. 2026Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guaranteescited by 7
  3. 2025Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG)cited by 5
  4. 2025Towards Copyright Protection for Knowledge Bases of Retrieval-augmented Language Models via Reasoningcited by 4
  5. 2025A Survey of LLM × DATAcited by 4
  6. 2025Exposing Privacy Risks in Graph Retrieval-Augmented Generationcited by 4
  7. 2026Observable Channels, Not Just Storage: Evaluating Privacy Leakage in LLM Agent Pipelinescited by 4
  8. 2026Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agentscited by 4
  9. 2025ALoFTRAG: Automatic Local Fine Tuning for Retrieval Augmented Generationcited by 3
  10. 2025Securing RAG: A Risk Assessment and Mitigation Frameworkcited by 3
  11. 2025Learning to Erase Private Knowledge from Multi-Documents for Retrieval-Augmented Large Language Modelscited by 2
  12. 2025Distributed Retrieval-Augmented Generationcited by 2
  13. 2025Retrieval-Augmented Generation for Service Discovery: Chunking Strategies and Benchmarkingcited by 2
  14. 2025Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Privatecited by 2
  15. 2025Privacy Challenges and Solutions in Retrieval-Augmented Generation-Enhanced LLMs for Healthcare Chatbots: A Review of Applications, Risks, and Future Directionscited by 2
  16. 2026FedMosaic: Federated Retrieval-Augmented Generation via Parametric Adapterscited by 2
  17. 2026MemPot: Defending Against Memory Extraction Attack with Optimized Honeypotscited by 2
  18. 2026Differentially Private Retrieval-Augmented Generationcited by 2
  19. 2026Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directionscited by 2
  20. 2025Diverse And Private Synthetic Datasets Generation for RAG evaluation: A multi-agent frameworkcited by 1
  21. 2025A Decentralized Retrieval Augmented Generation System with Source Reliabilities Secured on Blockchaincited by 1
  22. 2026Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generationcited by 1
  23. 2026Needle-in-RAG: Prompt-Conditioned Character-Level Traceback of Poisoned Spans in Retrieved Evidencecited by 1
  24. 2026DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generationcited by 1
  25. 2025The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generationcited by 0
  26. 2025Membership Inference Attacks on In-Context Examples in LLM-based Recommender Systemscited by 0
  27. 2025RAGFort: Dual-Path Defense Against Proprietary Knowledge Base Extraction in Retrieval-Augmented Generationcited by 0
  28. 2026Improving User Privacy in Personalized Generation: Client-Side Retrieval-Augmented Modification of Server-Side Generated Speculationscited by 0
  29. 2026Graphs Don't Stay Secret: Practical Subgraph Reconstruction Attacks on Defended Graph RAGcited by 0
  30. 2026SEAL-Tag: Self-Tag Evidence Aggregation with Probabilistic Circuits for PII-Safe Retrieval-Augmented Generationcited by 0
  31. 2026AI Engineering Blueprint for On-Premises Retrieval-Augmented Generation Systemscited by 0
  32. 2026Detecting RAG Extraction Attack via Dual-Path Runtime Integrity Gamecited by 0
  33. 2026A Case Study on the Impact of Anonymization Along the RAG Pipelinecited by 0
  34. 2026Privacy Without Losing Place: A Paradigm for Private Retrieval in Spatial RAGscited by 0
  35. 2026Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelitycited by 0
  36. 2026Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agentscited by 0
  37. 2026Is External Database Protection Static in Retrieval-Augmented Generation? Rethinking Privacy Preservation under Dynamic Queriescited by 0
  38. 2026Privacy-Preserving RAG by Concealing Sensitive Information from External LLMscited by 0

50 most cited of 52 All 52 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems
  2. 2024RAG with Differential Privacy
  3. 2026Not All Entities are Created Equal: A Dynamic Anonymization Framework for Privacy-Preserving RAG
  4. 2025Privacy-Aware RAG: Secure and Isolated Knowledge Retrieval
  5. 2026SD-RAG: A Prompt-Injection-Resilient Framework for Selective Disclosure in Retrieval-Augmented Generation
  6. 2026RAG-CT: Mitigating Privacy Risks on Retrieval-Augmented Generation Systems via Scanning Prompt Distribution
  7. 2026PRAG: End-to-End Privacy-Preserving Retrieval-Augmented Generation
  8. 2024Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases