mlsanityData to 14 Oct 2026

Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG)

arXiv 2510.06719 ↗First posted 8 Oct 2025cs.CR cs.CL cs.LGcited by 6

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

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by grounding them in external knowledge. However, its application in sensitive domains is limited by privacy risks. Existing private RAG methods typically rely on query-time differential privacy (DP), which requires repeated noise injection and leads to accumulated privacy loss. To address this issue, we propose DP-SynRAG, a framework that uses LLMs to generate differentially private synthetic RAG databases. Unlike prior methods, the synthetic text can be reused once created, thereby avoiding repeated noise injection and additional privacy costs. To preserve essential information for downstream RAG tasks, DP-SynRAG extends private prediction, which instructs LLMs to generate text that mimics subsampled database records in a DP manner. Experiments show that DP-SynRAG achieves superior performance to the state-of-the-art private RAG systems while maintaining a fixed privacy budget, offering a scalable solution for privacy-preserving RAG.

Key facts. Cited by 6 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 29 of its 43 references that are in the map. First posted on arXiv 8 Oct 2025.

Builds on

29 of 43 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025Safeguarding Privacy of Retrieval Data against Membership Inference Attacks: Is This Query Too Close to Home?28 May
  2. 2025Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries21 May
  3. 2025Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation1 Feb
  4. 2024RAG with Differential Privacy26 Dec
  5. 2024Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy6 Dec
  6. 2024Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications21 Nov
  7. 2024Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors3 Nov
  8. 2024Mask-based Membership Inference Attacks for Retrieval-Augmented Generation26 Oct
  9. 2024Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data20 Jun
  10. 2024Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems27 Feb
  11. 2024The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)23 Feb

Other references · 18

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  5. 2025Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAscited by 521
  6. 2016Concentrated Differential Privacy: Simplifications, Extensions, and Lower Boundscited by 346
  7. 2017SearchQA: A New Q&A Dataset Augmented with Context from a Search Enginecited by 225
  8. 2022Synthetic Text Generation with Differential Privacy: A Simple and Practical Recipecited by 108
  9. 2023Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generationcited by 96
  10. 2021Differential Privacy for Text Analytics via Natural Text Sanitizationcited by 77
  11. 2024Differentially Private Synthetic Data via Foundation Model APIs 2: Textcited by 76
  12. 2023Harnessing large-language models to generate private synthetic textcited by 65
6 more
  1. 2023DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineercited by 57
  2. 2022A Customized Text Sanitization Mechanism with Differential Privacycited by 52
  3. 2024Private prediction for large-scale synthetic text generationcited by 24
  4. 2021Making the Most of Parallel Composition in Differential Privacycited by 10
  5. 2024Data-adaptive Differentially Private Prompt Synthesis for In-Context Learningcited by 10
  6. 2025Clustering and Median Aggregation Improve Differentially Private Inferencecited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026Query-Efficient Agentic Graph Extraction Attacks on GraphRAG Systemscited by 3
  2. 2026Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directionscited by 2
  3. 2026Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agentscited by 0
  4. 2026As We May Searchcited by 0
  5. 2026Is External Database Protection Static in Retrieval-Augmented Generation? Rethinking Privacy Preservation under Dynamic Queriescited by 0
  6. 2026ScoreShield: Differentially Private Release of Similarity Scorescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Private
  2. 2026Differentially Private Retrieval-Augmented Generation
  3. 2025InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy
  4. 2024Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation
  5. 2024RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service
  6. 2026SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systems
  7. 2026P2RAG: Efficient Privacy-Preserving RAG Service Supporting Arbitrary Top-k Retrieval
  8. 2025SynBench: A Benchmark for Differentially Private Text Generation