Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks

TL;DR

This paper provides the first comprehensive survey of security threats, defenses, and benchmarks for Retrieval-Augmented Generation systems, aiming to enhance their robustness and trustworthiness.

Contribution

It systematically analyzes RAG vulnerabilities, categorizes defense strategies, and consolidates evaluation benchmarks, offering a unified end-to-end security assessment framework.

Findings

Identifies core threat vectors like data poisoning and adversarial attacks.

Summarizes defense mechanisms including encryption and differential privacy.

Establishes a unified benchmark for RAG security evaluation.

Abstract

Retrieval-Augmented Generation (RAG) significantly mitigates the hallucinations and domain knowledge deficiency in large language models by incorporating external knowledge bases. However, the multi-module architecture of RAG introduces complex system-level security vulnerabilities. Guided by the RAG workflow, this paper analyzes the underlying vulnerability mechanisms and systematically categorizes core threat vectors such as data poisoning, adversarial attacks, and membership inference attacks. Based on this threat assessment, we construct a taxonomy of RAG defense technologies from a dual perspective encompassing both input and output stages. The input-side analysis reviews data protection mechanisms including dynamic access control, homomorphic encryption retrieval, and adversarial pre-filtering. The output-side examination summarizes advanced leakage prevention techniques such as federated learning isolation, differential privacy perturbation, and lightweight data sanitization. To establish a unified benchmark for future experimental design, we consolidate authoritative test datasets, security standards, and evaluation frameworks. To the best of our knowledge, this paper presents the first end-to-end survey dedicated to the security of RAG systems. Distinct from existing literature that isolates specific vulnerabilities, we systematically map the entire pipeline-providing a unified analysis of threat models, defense mechanisms, and evaluation benchmarks. By enabling deep insights into potential risks, this work seeks to foster the development of highly robust and trustworthy next-generation RAG systems.