mlsanityData to 14 Oct 2026

Secure Multifaceted-RAG for Enterprise: Hybrid Knowledge Retrieval with Security Filtering

arXiv 2504.13425 ↗First posted 18 Apr 2025cs.CLcited by 0

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

Abstract (arXiv)

Existing Retrieval-Augmented Generation (RAG) systems face challenges in enterprise settings due to limited retrieval scope and data security risks. When relevant internal documents are unavailable, the system struggles to generate accurate and complete responses. Additionally, using closed-source Large Language Models (LLMs) raises concerns about exposing proprietary information. To address these issues, we propose the Secure Multifaceted-RAG (SecMulti-RAG) framework, which retrieves not only from internal documents but also from two supplementary sources: pre-generated expert knowledge for anticipated queries and on-demand external LLM-generated knowledge. To mitigate security risks, we adopt a local open-source generator and selectively utilize external LLMs only when prompts are deemed safe by a filtering mechanism. This approach enhances completeness, prevents data leakage, and reduces costs. In our evaluation on a report generation task in the automotive industry, SecMulti-RAG significantly outperforms traditional RAG - achieving 79.3 to 91.9 percent win rates across correctness, richness, and helpfulness in LLM-based evaluation, and 56.3 to 70.4 percent in human evaluation. This highlights SecMulti-RAG as a practical and secure solution for enterprise RAG.

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 10 of its 24 references that are in the map. First posted on arXiv 18 Apr 2025.

Builds on

10 of 24 references.

References · 10

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  3. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  4. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
  5. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 298
  6. 2023Analyzing Leakage of Personally Identifiable Information in Language Modelscited by 285
  7. 2017LOGAN: Membership Inference Attacks Against Generative Modelscited by 28
  8. 2024"Ghost of the past": identifying and resolving privacy leakage from LLM's memory through proactive user interactioncited by 10
  9. 2024AssistRAG: Boosting the Potential of Large Language Models with an Intelligent Information Assistantcited by 5
  10. 2024A Multi-Source Retrieval Question Answering Framework Based on RAGcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024RAG Does Not Work for Enterprises
  2. 2025Privacy-Aware RAG: Secure and Isolated Knowledge Retrieval
  3. 2025A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions
  4. 2024Pirates of the RAG: Adaptively Attacking LLMs to Leak Knowledge Bases
  5. 2025MES-RAG: Bringing Multi-modal, Entity-Storage, and Secure Enhancements to RAG
  6. 2026Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions
  7. 2025Engineering the RAG Stack: A Comprehensive Review of the Architecture and Trust Frameworks for Retrieval-Augmented Generation Systems
  8. 2025RAG Security and Privacy: Formalizing the Threat Model and Attack Surface