Retrieval-Augmented Generation (RAG) significantly enhances Large Language Models (LLMs), but simultaneously exposes a critical vulnerability to knowledge poisoning attacks. Existing attack methods like PoisonedRAG remain detectable due to coarse-grained separate-and-concatenate strategies. To bridge this gap, we propose RefineRAG, a novel framework that treats poisoning as a holistic word-level refinement problem. It operates in two stages: Macro Generation produces toxic seeds guaranteed to induce target answers, while Micro Refinement employs a retriever-in-the-loop optimization to maximize retrieval priority without compromising naturalness. Evaluations on NQ and MSMARCO demonstrate that RefineRAG achieves state-of-the-art effectiveness, securing a 90% Attack Success Rate on NQ, while registering the lowest grammar errors and repetition rates among all baselines. Crucially, our proxy-optimized attacks successfully transfer to black-box victim systems, highlighting a severe practical threat.
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)
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)
Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation
Faculty of Information Technology, University of Science(胡志明市科学大学信息技术学院);Vietnam National University, Ho Chi Minh City(越南国家大学胡志明市分校);Virginia Tech(弗吉尼亚理工大学);Indiana University(印第安纳大学);University College Cork(科克大学学院);National University of Singapore(新加坡国立大学);VNU University of Engineering and Technology(越南国家大学工程技术大学);The Pennsylvania State University(宾夕法尼亚州立大学)
On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains
Department of ECE University of Minnesota(电子工程系明尼苏达大学);Data Science Institute University of Chicago(数据科学研究所芝加哥大学);Carlson School of Management University of Minnesota(卡尔森管理学院明尼苏达大学);Department of Surgery University of Minnesota(外科系明尼苏达大学);Cisco Research(思科研究);School of Statistics University of Minnesota(统计学学院明尼苏达大学)