paperAugust 2026Unreviewed

Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation

Minh Tran, Cuong Dang, Tuc Nguyen, Khanh-Tung Tran, Minh Huynh Nguyen, Trinh Chau, Kien Le, Do Xuan Long, Jiahao Zhang, Fali Wang, Hoang D. Nguyen, Thanh Le, Suhang Wang

View resource PDF

Abstract

Retrieval-Augmented Generation (RAG) enhances large language models by grounding outputs in external knowledge, improving factuality and reducing hallucinations. At the same time, the retrieval-augmented pipeline introduces new robustness and security risks, including corpus poisoning, backdoor attacks, privacy leakage, and fairness violations. Despite rapid progress in this area, existing surveys remain limited in their treatment of attacker objectives, threat models, and stage-specific defense

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

Suggested from the entry's categories.

Cite

@misc{tran2026retrieved,
  title = {{Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation}},
  author = {Minh Tran and Cuong Dang and Tuc Nguyen and Khanh-Tung Tran and Minh Huynh Nguyen and Trinh Chau and Kien Le and Do Xuan Long and Jiahao Zhang and Fali Wang and Hoang D. Nguyen and Thanh Le and Suhang Wang},
  year = {2026},
  month = aug,
  eprint = {2608.24977},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.24977}
}