Retrieval-Augmented Generation (RAG) systems enhance large language models by grounding responses in retrieved documents from external knowledge sources at inference time. However, this reliance on retrieved content introduces vulnerabilities to poisoning attacks, in which adversarial documents can manipulate both the retrieval process and the generated outputs. This paper investigates poisoning robustness in RAG through a full factorial experimental study covering 432 configurations. We analyze the impacts of dataset, retriever type, retrieval depth, database composition, chunking strategy, and generator model on retrieval-level and generation-level metrics. The results show that retriever architecture, dataset, and retrieval depth are the strongest factors affecting poisoning exposure, while generator choice and database composition have a major impact on downstream attack success. Dense and graph-based retrievers generally improve robustness relative to BM25, whereas larger retrieval depth increases the likelihood of retrieving poisoned passages. We further show that replicating poisoned content across multiple databases amplifies adversarial influence, while additional clean sources can mitigate it. These findings highlight that poisoning vulnerability in RAG is not attributable to a single component, but instead arises from the interaction of retrieval, generation, and knowledge-base configuration.
PURPOSE: Poisoning Conflict Resolution in RAG via Proxy-Fact-Grounded Updates
School of Computer Science, Nanjing University(南京大学计算机科学学院);State Key Laboratory for Novel Software Technology, Nanjing University(南京大学计算机软件新技术国家重点实验室)
Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control
Zhejiang University(浙江大学);Binjiang Institute of Zhejiang University(浙江大学滨江研究院);Shanghai Jiao Tong University(上海交通大学);Zhejiang Lab(浙江实验室);Harbin Institute of Technology(哈尔滨工业大学);Hangzhou Dianzi University(杭州电子科技大学)
RAG Safety: Exploring Knowledge Poisoning Attacks to Retrieval-Augmented Generation
School of Computer Science and Technology,Xi'an Jiaotong University(西安交通大学计算机科学与技术学院);Department of Computer Science, The University of Manchester(曼彻斯特大学计算机科学系);School of Computer Science and Engineering, Southeast University(东南大学计算机科学与工程学院);National University of Singapore(新加坡国立大学)
When Poison Fails After Retrieval: Revisiting Corpus Poisoning under Chunking and Reranking Pipelines
School of Computer Science, Shandong University(山东大学计算机学院);School of Information, Shandong University(山东大学信息学院);School of Software Engineering, Shandong University(山东大学软件学院)
Bias Amplification in RAG: Poisoning Knowledge Retrieval to Steer LLMs
Faculty of Data Science, City University of Macau(数据科学学院,澳门城市大学);Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences)(计算能力网络与信息安全重点实验室,教育部,山东计算机科学中心,齐鲁工业大学(山东科学院));Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science(山东省计算能力互联网与服务计算重点实验室,山东省计算机科学基础研究中心)
One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems
State Key Laboratory of Intelligent Game(智能游戏国家重点实验室);Science and Technology on Integrated Information System Laboratory, Institute of Software Chinese Academy of Sciences(中国科学院软件研究所综合信息系统技术国家级重点实验室);University of Chinese Academy of Sciences(中国科学院大学);Nanyang Technological University(南洋理工大学)
Right Facts, Wrong Rule: Scope-Transfer Poisoning of Retrieval-Augmented Generation
School of Cyber Science and Technology, Harbin Institute of Technology(哈尔滨工业大学网络空间安全学院);SnT, University of Luxembourg(卢森堡大学科学与技术学院);Department of New Networks, Peng Cheng Laboratory(鹏城实验室新网络部)
RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis
School of Computer Science, Fudan University(复旦大学计算机科学学院);Department of Computer Science, Worcester Polytechnic Institute(沃思堡理工学院计算机科学系);Institute of Big Data, Fudan University(复旦大学大数据研究院)
Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation
Tsinghua University(清华大学);Beijing University of Posts and Telecommunications(北京邮电大学);Northwestern Polytechnical University(西北工业大学);ETH Zurich(苏黎世联邦理工学院)
Hidden in the Metadata: Stealth Poisoning Attacks on Multimodal Retrieval-Augmented Generation
The City University of New York, CSI, Staten Island, NY 10314, USA(纽约城市大学,CSI,史泰登岛分校);The City University of New York, Graduate Center, New York, NY 10016, USA(纽约城市大学研究生中心)
AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases
University of Chicago(芝加哥大学);University of Illinois, Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);University of Wisconsin, Madison(威斯康星大学麦迪逊分校);University of California, Berkeley(加州大学伯克利分校)