Awesome-RAG-Security

News

Initial release: This repository records papers on RAG security following the SLOT taxonomy from our survey.

A Survey of Secure Retrieval-Augmented Generation

Yuming Xu ¹, Mingtao Zhang ¹, Zhuohan Ge ¹, Haoyang Li ¹, Nicole Hu ¹, Yongqi Zhang ², Zhiyuan Wen ¹, Jason Chen Zhang ¹, Qing Li ¹, Lei Chen ²

¹The Hong Kong Polytechnic University, ²The Hong Kong University of Science and Technology (Guangzhou).

@article{xu2026securing,
  title={A Survey of Secure Retrieval-Augmented Generation},
  author={Xu, Yuming and Zhang, Mingtao and Ge, Zhuohan and Li, Haoyang and Hu, Nicole and Zhang, Yongqi and Wen, Zhiyuan and Zhang, Jason Chen and Li, Qing and Chen, Lei},
  journal={arXiv preprint arXiv:2604.08304},
  year={2026}
}

If you would like to include your paper, suggest improvements to our survey, or discuss related topics with us, please feel free to contact: [email protected].

_{Attack surfaces (S1-S4) and defense layers that mirror them (L1-L4) along the RAG pipeline.}

_{SLOT view of the RAG knowledge-access pipeline. Attack surfaces (S1-S4) and defense layers (L1-L4) are aligned with the pipeline stages, while Objective (O) and Target (T) are cross-cutting tags used to compare attacks, defenses, and benchmarks, i.e., SLOT Tag = Surface/Layer + Objective + Target.}

Taxonomy and Papers

• Awesome-RAG-Security
• Attack Mechanisms
  • Knowledge Poisoning (S1)
  • Retrieval Result Manipulation (S2)
  • Retrieved-Context Exploitation (S3)
  • Private Knowledge Extraction (S4)
• Defenses and Remediation Mechanisms
  • Knowledge-Base Integrity and Remediation (L1)
  • Retrieval-Time Access Hardening (L2)
  • Post-Retrieval Context Isolation (L3)
  • Access Control, Privacy and Confidentiality (L4)
• Secure-RAG Evaluation Studies
  • Benchmark Studies
  • Systematic Evaluation Studies
• Screening Protocol and Released Records

---

Attack Mechanisms

Knowledge Poisoning (S1)

Query-Specific Corpus Poisoning (To Top)

Year	Title	Surface/Layer	Objective	Target	Venue	Official Link
2026	Practical Poisoning Attacks against Retrieval-Augmented Generation (CorruptRAG)	S1; sec: S2	O1	T1	SACMAT	Paper
2026	RIPRAG: Hack a Black-box Retrieval-Augmented Generation Question-Answering System with Reinforcement Learning	S1; sec: S2	O1	T1	Findings of ACL	Paper
2026	Token-Level Precise Attack on RAG: Searching for the Best Alternatives to Mislead Generation	S1; sec: S2	O1	T1	Findings of EACL	Paper
2026	Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems	S1; sec: S2, S3	O1	T1	AAAI	Paper Code
2025	The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems	S1; sec: S2	O1	T1	Findings of ACL	Paper Code
2025	One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems (AuthChain)	S1; sec: S2	O1	T1	Findings of EMNLP	Paper Code
2025	The RAG Paradox: A Black-Box Attack Exploiting Unintentional Vulnerabilities in Retrieval-Augmented Generation Systems	S1; sec: S2	O1	T1	Findings of EMNLP	Paper
2025	PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models	S1; sec: S2	O1	T1	USENIX Security	Paper Code
2024	Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-Level Perturbations (GARAG)	S1; sec: S2	O1	T1	Findings of EMNLP	Paper
2024	Human-Imperceptible Retrieval Poisoning Attacks in LLM-Powered Applications	S1; sec: S3	O1	T1	FSE Companion	Paper
2024	HijackRAG: Hijacking Attacks against Retrieval-Augmented Large Language Models	S1; sec: S2, S3	O1	T1	arXiv	Paper Code

Trigger / Generalized Poisoning (To Top)