# FRAG: Toward Federated Vector Database Management for Collaborative and Secure Retrieval-Augmented Generation

arXiv: https://arxiv.org/abs/2410.13272 · HTML: https://mlsanity.com/paper/2410.13272/

## Key facts

- Cited by 12 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 12 of its 48 references that are in the map.
- First posted on arXiv 17 Oct 2024.

## Placed in

- Retrieval-augmented generation / [Privacy and security of RAG](https://mlsanity.com/rag/privacy-and-security-of-rag/)

## Builds on (most cited first, 12 of 12)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [Analyzing Federated Learning through an Adversarial Lens](https://mlsanity.com/paper/1811.12470/) (2018)
- [FedML: A Research Library and Benchmark for Federated Machine Learning](https://mlsanity.com/paper/2007.13518/) (2020)
- [TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption](https://mlsanity.com/paper/2104.03152/) (2021)
- [FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective](https://mlsanity.com/paper/2110.13864/) (2021)
- [Byzantine-Resilient High-Dimensional Federated Learning](https://mlsanity.com/paper/2006.13041/) (2020)

## Built on by (most cited first, 12 of 12)

- [A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions](https://mlsanity.com/paper/2507.18910/) (2025)
- [Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions](https://mlsanity.com/paper/2503.16585/) (2025)
- [Talk to Right Specialists: Iterative Routing in Multi-agent Systems for Question Answering](https://mlsanity.com/paper/2501.07813/) (2025)
- [HetaRAG: Hybrid Deep Retrieval-Augmented Generation across Heterogeneous Data Stores](https://mlsanity.com/paper/2509.21336/) (2025)
- [Distributed Retrieval-Augmented Generation](https://mlsanity.com/paper/2505.00443/) (2025)
- [Efficient Federated Search for Retrieval-Augmented Generation using Lightweight Routing](https://mlsanity.com/paper/2502.19280/) (2025)
- [Synapse: Federated Tool Routing via Typed Compendium Artifacts](https://mlsanity.com/paper/2602.00911/) (2026)
- [Supercharging Federated Intelligence Retrieval](https://mlsanity.com/paper/2603.25374/) (2026)
- [PRAG: End-to-End Privacy-Preserving Retrieval-Augmented Generation](https://mlsanity.com/paper/2604.26525/) (2026)
- [Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generation](https://mlsanity.com/paper/2609.22162/) (2026)
- [Federated Agent Optimization](https://mlsanity.com/paper/2610.01195/) (2026)
- [Mapping the RAG Landscape: A Four Axis Taxonomy of Efficiency, Defense, Interactivity, and Reasoning](https://mlsanity.com/paper/2610.01936/) (2026)

## Abstract (arXiv)

This paper introduces textitFederated Retrieval-Augmented Generation (FRAG), a novel database management paradigm tailored for the growing needs of retrieval-augmented generation (RAG) systems, which are increasingly powered by large-language models (LLMs). FRAG enables mutually-distrusted parties to collaboratively perform Approximate k-Nearest Neighbor (ANN) searches on encrypted query vectors and encrypted data stored in distributed vector databases, all while ensuring that no party can gain any knowledge about the queries or data of others. Achieving this paradigm presents two key challenges: (i) ensuring strong security guarantees, such as Indistinguishability under Chosen-Plaintext Attack (IND-CPA), under practical assumptions (e.g., we avoid overly optimistic assumptions like non-collusion among parties); and (ii) maintaining performance overheads comparable to traditional, non-federated RAG systems. To address these challenges, FRAG employs a single-key homomorphic encryption protocol that simplifies key management across mutually-distrusted parties. Additionally, FRAG introduces a textitmultiplicative caching technique to efficiently encrypt floating-point numbers, significantly improving computational performance in large-scale federated environments. We provide a rigorous security proof using standard cryptographic reductions and demonstrate the practical scalability and efficiency of FRAG through extensive experiments on both benchmark and real-world datasets.