mlsanityData to 14 Oct 2026

Privacy-Preserving RAG by Concealing Sensitive Information from External LLMs

arXiv 2608.12675 ↗First posted 13 Aug 2026cs.AI cs.CRcited by 0

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

Abstract (arXiv)

Retrieval-Augmented Generation (RAG) is widely used to improve the performance of Large Language Models (LLMs) in answering user queries. Existing privacy research on RAG has focused on preventing unauthorized users from accessing sensitive data. However, another important problem that is often overlooked in RAG privacy research is that external generators have access to the query and the retrieved documents, which may contain confidential information that could potentially be misused or accessed for unintended purposes. In this paper, we introduce the Sensitive Entity Alias Generator (SEAG), a privacy-preserving framework that empowers users to utilize powerful third-party generators without disclosing sensitive information. SEAG introduces a lightweight model that locates sensitive entities, generates corresponding aliases, and constructs an entity replacement table. The table is used to replace sensitive words in the user's query and in the retrieved documents before they are forwarded to an external generator. For this purpose, two datasets were constructed: one for fine-tuning SEAG models to generate entity replacement tables, and another for evaluating the entire SEAG framework. The experimental results demonstrate the success of the SEAG framework. As for the User metric, which measures the ability of the model to provide a correct response to the user while hiding sensitive information from the external generator, all SEAG models achieved over 80% accuracy. Additional analysis further evaluated the ability of SEAG models Qwen-3, LLaMA-3.2, and Phi-4 to hide all sensitive entities within given documents. The results show good performance with total accuracies of 77.83%, 76.73%, and 74.91%, respectively.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation. Builds on 14 of its 33 references that are in the map. First posted on arXiv 13 Aug 2026.

Builds on

14 of 33 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications21 Nov
  2. 2024Mask-based Membership Inference Attacks for Retrieval-Augmented Generation26 Oct
  3. 2024Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data20 Jun
  4. 2024Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation30 May
  5. 2024The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)23 Feb

Other references · 9

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  3. 2025Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAscited by 521
  4. 2023ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledgecited by 325
  5. 2023Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Biascited by 232
  6. 2024Trustworthiness in Retrieval-Augmented Generation Systems: A Surveycited by 83
  7. 2024Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Modelscited by 25
  8. 2025ALoFTRAG: Automatic Local Fine Tuning for Retrieval Augmented Generationcited by 3
  9. 2025AI Text Detectors and the Misclassification of Slightly Polished Arabic Textcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation
  2. 2024RAG with Differential Privacy
  3. 2026Not All Entities are Created Equal: A Dynamic Anonymization Framework for Privacy-Preserving RAG
  4. 2024Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy
  5. 2026SoK: Privacy Risks and Mitigations in Retrieval-Augmented Generation Systems
  6. 2025Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Private
  7. 2026Is External Database Protection Static in Retrieval-Augmented Generation? Rethinking Privacy Preservation under Dynamic Queries
  8. 2026A Case Study on the Impact of Anonymization Along the RAG Pipeline