arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.05087cs.IR
收藏

通过近似贪婪梯度下降进行语料库投毒

Corpus Poisoning via Approximate Greedy Gradient Descent

Jinyan Su, Preslav Nakov, Claire Cardie

AI总结:

本文提出 AGGD 攻击方法,用结构化搜索改进 HotFlip 以生成更高质量的对抗性 token 扰动,在多个数据集和检索器上显著提升语料库投毒成功率,并可泛化及用于 RAG 知识投毒。

摘要:

密集检索器广泛应用于信息检索,并且也已成功扩展到其他知识密集型领域,例如语言模型中的检索增强生成(RAG)系统。不幸的是,近来研究表明它们容易受到语料库投毒攻击:恶意用户将一小部分对抗性段落注入检索语料库,以诱使系统在大量用户查询的排名靠前结果中返回这些段落。需要进一步研究这些攻击在多大程度上可能限制密集检索器在真实应用中的部署。在本工作中,我们提出了近似贪婪梯度下降(AGGD),这是一种针对密集检索系统的新型攻击,它基于广泛使用的 HotFlip 方法来高效生成对抗性段落。我们证明,AGGD 通过用更结构化的搜索替代 HotFlip 的随机 token 采样,能够选择比 HotFlip 质量更高的 token 级扰动集合。实验表明,我们的方法在多个数据集和多种检索器上均取得很高的攻击成功率,并且能够泛化到未见过的查询和新领域。值得注意的是,我们的方法在攻击 ANCE 检索模型时极其有效:在 NQ 和 MS MARCO 数据集上,其攻击成功率相比 HotFlip 分别高出 15.24% 和 17.44%。此外,我们还展示了 AGGD 有潜力在其他对抗攻击中替代 HotFlip,例如对 RAG 系统的知识投毒。

英文摘要:

Dense retrievers are widely used in information retrieval and have also been successfully extended to other knowledge intensive areas such as language models, e.g., Retrieval-Augmented Generation (RAG) systems. Unfortunately, they have recently been shown to be vulnerable to corpus poisoning attacks in which a malicious user injects a small fraction of adversarial passages into the retrieval corpus to trick the system into returning these passages among the top-ranked results for a broad set of user queries. Further study is needed to understand the extent to which these attacks could limit the deployment of dense retrievers in real-world applications. In this work, we propose Approximate Greedy Gradient Descent (AGGD), a new attack on dense retrieval systems based on the widely used HotFlip method for efficiently generating adversarial passages. We demonstrate that AGGD can select a higher quality set of token-level perturbations than HotFlip by replacing its random token sampling with a more structured search. Experimentally, we show that our method achieves a high attack success rate on several datasets and using several retrievers, and can generalize to unseen queries and new domains. Notably, our method is extremely effective in attacking the ANCE retrieval model, achieving attack success rates that are 15.24\% and 17.44\% higher on the NQ and MS MARCO datasets, respectively, compared to HotFlip. Additionally, we demonstrate AGGD's potential to replace HotFlip in other adversarial attacks, such as knowledge poisoning of RAG systems.

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。

↑