paperMarch 2026Unreviewed

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

Yanming Mu, Hao Hu, Feiyang Li, Qiao Yuan, Jiang Wu, Zichuan Liu, Pengcheng Liu, Mei Wang, Hongwei Zhou, Yuling Liu

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

Framework mappings

OWASP Top 10 for LLM Applications

LLM02Sensitive Information Disclosure
LLM04Data and Model Poisoning

MITRE ATLAS

AML.T0020Poison Training Data
AML.T0024.000Infer Training Data Membership
AML.T0043Craft Adversarial Data

Suggested from the entry's categories.

Cite

@misc{mu2026secure,
  title = {{Towards Secure Retrieval-Augmented Generation: A Comprehensive Review of Threats, Defenses and Benchmarks}},
  author = {Yanming Mu and Hao Hu and Feiyang Li and Qiao Yuan and Jiang Wu and Zichuan Liu and Pengcheng Liu and Mei Wang and Hongwei Zhou and Yuling Liu},
  year = {2026},
  month = mar,
  eprint = {2603.21654},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.21654}
}