arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.16902cs.IR
收藏

文档截图检索器易受像素投毒攻击

Document Screenshot Retrievers are Vulnerable to Pixel Poisoning Attacks

Shengyao Zhuang, Ekaterina Khramtsova, Xueguang Ma, Bevan Koopman, Jimmy Lin, Guido Zuccon

AI总结:

本文提出三种针对基于视觉语言模型的文档截图检索器的像素投毒攻击方法,发现注入单张对抗性截图即可显著破坏检索结果,揭示了该类模型部署的潜在安全风险。

摘要:

近期密集检索的进展引入了基于视觉语言模型(VLM)的检索器,如DSE和ColPali,它们利用嵌入为向量的文档截图来实现有效搜索,并提供了比传统纯文本方法更简化的流程。在本研究中,我们提出了三种像素投毒攻击方法,旨在破坏基于VLM的检索器,并在各种攻击设置和参数配置下评估其有效性。我们的实证结果表明,向检索语料库中注入哪怕单张对抗性截图也能显著干扰搜索结果,在DSE的情况下能使41.9%查询的top-10检索文档被投毒,ColPali则为26.4%。这些漏洞率显著超过了对纯文本检索器进行同等攻击时所观察到的比率。此外,当针对一小组已知查询时,攻击成功率上升,在某些情况下实现了完全成功。通过揭示视觉语言模型固有的漏洞,本工作凸显了与其部署相关的潜在风险。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑