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

TL;DR

FRAG is a new federated database system enabling secure, privacy-preserving vector searches for large language model applications, balancing strong security with practical performance.

Contribution

FRAG introduces a novel federated vector database management paradigm with secure encrypted searches and a multiplicative caching technique for efficiency.

Findings

Achieves IND-CPA security under practical assumptions.

Demonstrates scalable performance on large datasets.

Provides rigorous security proofs and extensive experimental validation.

Abstract

This paper introduces \textit{Federated 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 \textit{multiplicative 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.