arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.14867cs.IR
收藏

面向主题的黑盒神经排序模型对抗攻击

Topic-oriented Adversarial Attacks against Black-box Neural Ranking Models

Yu-An Liu, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke, Wei Chen, Yixing Fan, Xueqi Cheng

AI总结:

该研究提出面向主题的黑盒神经排序模型对抗攻击任务,构建基于代理排序模型、强化学习与主题导向奖励的攻击框架,实验证明其性能优于现有策略,凸显NRMs的实际应用风险。

摘要:

神经排序模型(NRMs)在信息检索领域已受到广泛关注。遗憾的是,NRMs可能继承通用神经网络的对抗脆弱性,这一点可能被黑帽搜索引擎优化从业者利用。近期,针对NRMs的对抗攻击已在成对攻击场景下展开研究,即针对特定查询为目标文档生成对抗扰动。本文聚焦于一种更具普遍性的扰动类型,提出了面向NRMs的主题导向对抗排序攻击任务,其目标是找到一种难以察觉的扰动,能够提升目标文档在一组同主题查询下的排名。我们为该任务定义了静态和动态两种设置,并重点研究基于决策的黑盒攻击。我们提出了一种基于代理排序模型的新型框架,以提升面向主题的攻击性能。该攻击问题被形式化为马尔可夫决策过程(MDP),并通过强化学习求解。具体而言,一个面向主题的奖励函数引导策略找到成功的对抗样本,使其在一组查询中尽可能多的查询下获得排名提升。实验结果表明,所提出的框架性能显著优于现有攻击策略,我们在结论中再次强调,NRMs在现实世界的应用存在潜在风险。

英文摘要:

Neural ranking models (NRMs) have attracted considerable attention in information retrieval. Unfortunately, NRMs may inherit the adversarial vulnerabilities of general neural networks, which might be leveraged by black-hat search engine optimization practitioners. Recently, adversarial attacks against NRMs have been explored in the paired attack setting, generating an adversarial perturbation to a target document for a specific query. In this paper, we focus on a more general type of perturbation and introduce the topic-oriented adversarial ranking attack task against NRMs, which aims to find an imperceptible perturbation that can promote a target document in ranking for a group of queries with the same topic. We define both static and dynamic settings for the task and focus on decision-based black-box attacks. We propose a novel framework to improve topic-oriented attack performance based on a surrogate ranking model. The attack problem is formalized as a Markov decision process (MDP) and addressed using reinforcement learning. Specifically, a topic-oriented reward function guides the policy to find a successful adversarial example that can be promoted in rankings to as many queries as possible in a group. Experimental results demonstrate that the proposed framework can significantly outperform existing attack strategies, and we conclude by re-iterating that there exist potential risks for applying NRMs in the real world.

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。

↑