mlsanityData to 14 Oct 2026

Privacy-Aware RAG: Secure and Isolated Knowledge Retrieval

arXiv 2503.15548 ↗First posted 17 Mar 2025cs.CR cs.AIcited by 10

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

Abstract (arXiv)

The widespread adoption of Retrieval-Augmented Generation (RAG) systems in real-world applications has heightened concerns about the confidentiality and integrity of their proprietary knowledge bases. These knowledge bases, which play a critical role in enhancing the generative capabilities of Large Language Models (LLMs), are increasingly vulnerable to breaches that could compromise sensitive information. To address these challenges, this paper proposes an advanced encryption methodology designed to protect RAG systems from unauthorized access and data leakage. Our approach encrypts both textual content and its corresponding embeddings prior to storage, ensuring that all data remains securely encrypted. This mechanism restricts access to authorized entities with the appropriate decryption keys, thereby significantly reducing the risk of unintended data exposure. Furthermore, we demonstrate that our encryption strategy preserves the performance and functionality of RAG pipelines, ensuring compatibility across diverse domains and applications. To validate the robustness of our method, we provide comprehensive security proofs that highlight its resilience against potential threats and vulnerabilities. These proofs also reveal limitations in existing approaches, which often lack robustness, adaptability, or reliance on open-source models. Our findings suggest that integrating advanced encryption techniques into the design and deployment of RAG systems can effectively enhance privacy safeguards. This research contributes to the ongoing discourse on improving security measures for AI-driven services and advocates for stricter data protection standards within RAG architectures.

Key facts. Cited by 10 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 24 of its 51 references that are in the map. First posted on arXiv 17 Mar 2025.

Builds on

24 of 51 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases24 Dec
  2. 2024Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems27 Feb
  3. 2024The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)23 Feb

Other references · 21

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  3. 2020Extracting Training Data from Large Language Modelscited by 2,189
  4. 2023A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivitycited by 894
  5. 2021Membership Inference Attacks From First Principlescited by 878
  6. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 792
  7. 2021Deduplicating Training Data Makes Language Models Bettercited by 714
  8. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  9. 2022Deduplicating Training Data Mitigates Privacy Risks in Language Modelscited by 314
  10. 2023Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarizationcited by 246
  11. 2023Mitigating the Alignment Tax of RLHFcited by 183
  12. 2023Lift Yourself Up: Retrieval-augmented Text Generation with Self Memorycited by 103
9 more
  1. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Surveycited by 83
  2. 2020A Survey on Text Classification: From Shallow to Deep Learningcited by 80
  3. 2023Towards Better Chain-of-Thought Prompting Strategies: A Surveycited by 62
  4. 2023A Practical Survey on Zero-shot Prompt Design for In-context Learningcited by 49
  5. 2022Memorization in NLP Fine-tuning Methodscited by 45
  6. 2023Exploring Memorization in Fine-tuned Language Modelscited by 45
  7. 2024HealthQ: Unveiling Questioning Capabilities of LLM Chains in Healthcare Conversationscited by 31
  8. 2024Unleashing Worms and Extracting Data: Escalating the Outcome of Attacks against RAG-based Inference in Scale and Severity Using Jailbreakingcited by 30
  9. 2024A review on the use of large language models as virtual tutorscited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 7.

10 papers.

  1. 2025A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directionscited by 31
  2. 2025Retrieval-Augmented Generation in Industry: An Interview Study on Use Cases, Requirements, Challenges, and Evaluationcited by 8
  3. 2026Query-Efficient Agentic Graph Extraction Attacks on GraphRAG Systemscited by 3
  4. 2026Making Theft Useless: Adulteration-Based Protection of Proprietary Knowledge Graphs in GraphRAG Systemscited by 2
  5. 2026Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directionscited by 2
  6. 2025AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMscited by 1
  7. 2026PRAG: End-to-End Privacy-Preserving Retrieval-Augmented Generationcited by 0
  8. 2026π-RAG: Oblivious Retrieval via Semantic Quantization and Transcendental Addressing for Large Language Modelscited by 0
  9. 2026Mitigating Database Leakage in RAG Systems with Keyword-Grounded Fact Substitutioncited by 0
  10. 2026Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoningcited by 0

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. 2026Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks
  3. 2026P2RAG: Efficient Privacy-Preserving RAG Service Supporting Arbitrary Top-k Retrieval
  4. 2025RAG Security and Privacy: Formalizing the Threat Model and Attack Surface
  5. 2025Provably Secure Retrieval-Augmented Generation
  6. 2024Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy
  7. 2025Securing RAG: A Risk Assessment and Mitigation Framework
  8. 2024RAG with Differential Privacy