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 2103.05248cs.LGcs.CVcs.IR
收藏

深度排序中的实用相对顺序攻击

Practical Relative Order Attack in Deep Ranking

Xi’an Jiaotong University(西安交通大学);Alibaba Group(阿里巴巴集团);HERE Technologies(HERE科技公司);Wormpex AI Research(Wormpex人工智能研究院)

Mo Zhou, Le Wang, Zhenxing Niu, Qilin Zhang, Yinghui Xu, Nanning Zheng, Gang Hua

摘要:

最近的研究揭示了深度排名模型的漏洞,其中一个不可察觉的扰动可能会引发排名结果的巨大变化。虽然以前的尝试侧重于操纵某些候选人的绝对排名,但调整其相对顺序的可能性仍然没有得到充分探讨。在本文中,我们提出了一种针对深度排名系统的新的对抗攻击,即,顺序攻击,根据攻击者指定的排列,秘密地改变一组选定的候选者之间的相对顺序,对其他不相关的候选者的干扰有限。具体来说,它被制定为一个三重式的损失强加一个不平等链反映指定的排列。然而,由于各种黑盒限制,这种白盒目标的直接优化在现实世界的攻击场景中是不可行的。为了应对这些问题,我们提出了一个短程排名相关性度量作为黑盒顺序攻击的替代目标,以近似白盒方法。订单攻击在Fashion-MNIST和Stanford-Online-Products数据集上进行评估,包括白盒和黑盒威胁模型。黑盒攻击也在一个主要的电子商务平台上成功实施。综合实验评估表明,所提出的方法的有效性,揭示了一种新的排序模型的脆弱性。

英文摘要:

Recent studies unveil the vulnerabilities of deep ranking models, where an imperceptible perturbation can trigger dramatic changes in the ranking result. While previous attempts focus on manipulating absolute ranks of certain candidates, the possibility of adjusting their relative order remains under-explored. In this paper, we formulate a new adversarial attack against deep ranking systems, i.e., the Order Attack, which covertly alters the relative order among a selected set of candidates according to an attacker-specified permutation, with limited interference to other unrelated candidates. Specifically, it is formulated as a triplet-style loss imposing an inequality chain reflecting the specified permutation. However, direct optimization of such white-box objective is infeasible in a real-world attack scenario due to various black-box limitations. To cope with them, we propose a Short-range Ranking Correlation metric as a surrogate objective for black-box Order Attack to approximate the white-box method. The Order Attack is evaluated on the Fashion-MNIST and Stanford-Online-Products datasets under both white-box and black-box threat models. The black-box attack is also successfully implemented on a major e-commerce platform. Comprehensive experimental evaluations demonstrate the effectiveness of the proposed methods, revealing a new type of ranking model vulnerability.

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。

↑