
Coleção curada de artigos de pesquisa sobre segurança de geração aumentada por recuperação, organizada pela taxonomia SLOT, abrangendo envenenamento de conhecimento, manipulação de recuperação, exploração de contexto e defesas.
Lançamento inicial: Este repositório reúne artigos sobre segurança em RAG seguindo a taxonomia SLOT da nossa pesquisa.
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}
}
Se você gostaria de incluir seu artigo, sugerir melhorias para nossa pesquisa ou discutir tópicos relacionados conosco, sinta-se à vontade para entrar em contato: [email protected].
Superfícies de ataque (S1-S4) e camadas de defesa que as espelham (L1-L4) ao longo do pipeline RAG.
Visão SLOT do pipeline de acesso ao conhecimento RAG. As superfícies de ataque (S1-S4) e as camadas de defesa (L1-L4) estão alinhadas com os estágios do pipeline, enquanto Objetivo (O) e Alvo (T) são tags transversais usadas para comparar ataques, defesas e benchmarks, ou seja, SLOT Tag = Superfície/Camada + Objetivo + Alvo.
| Ano | Título | Superfície/Camada | Objetivo | Alvo | Veículo | Link Oficial |
|---|---|---|---|---|---|---|
| 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 |