Recent advancements in dense retrieval have introduced vision-language model (VLM)-based retrievers, such as DSE and ColPali, which leverage document screenshots embedded as vectors to enable effective search and offer a simplified pipeline over traditional text-only methods. In this study, we propose three pixel poisoning attack methods designed to compromise VLM-based retrievers and evaluate their effectiveness under various attack settings and parameter configurations. Our empirical results demonstrate that injecting even a single adversarial screenshot into the retrieval corpus can significantly disrupt search results, poisoning the top-10 retrieved documents for 41.9% of queries in the case of DSE and 26.4% for ColPali. These vulnerability rates notably exceed those observed with equivalent attacks on text-only retrievers. Moreover, when targeting a small set of known queries, the attack success rate raises, achieving complete success in certain cases. By exposing the vulnerabilities inherent in vision-language models, this work highlights the potential risks associated with their deployment.
Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation
National Engineering Research Center for Software Engineering, Peking University(软件工程国家级工程研究中心,北京大学);City University of Hong Kong(香港城市大学);Peking University(北京大学);Tencent Technology(腾讯科技)
提出Chain of Evidence (CoE)框架,利用视觉语言模型直接对检索到的文档截图进行推理,输出精确边界框以可视化完整推理链,解决迭代检索增强生成中的粗粒度归因和视觉语义丢失问题。
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)