arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.09773cs.CVcs.AI
收藏

T-SEA:基于传输的自包围攻击目标检测

T-SEA: Transfer-based Self-Ensemble Attack on Object Detection

Peking University(北京大学)

Hao Huang, Ziyan Chen, Huanran Chen, Yongtao Wang, Kevin Zhang

摘要:

与基于查询的黑盒攻击相比,基于传输的黑盒攻击不需要被攻击模型的任何信息,从而保证了攻击的秘密性。然而,大多数现有的基于转移的方法依赖于集成多个模型来提高攻击的可转移性,这是时间和资源密集型的,更不用说在同一任务上获得不同模型的困难。为了解决这一问题,本文重点研究了基于单模型转移的目标检测黑盒攻击方法,利用一个模型实现对多个黑盒检测器的高转移性对抗攻击。具体来说,我们首先观察现有方法的补丁优化过程,并通过稍微调整其训练策略,提出了一个增强的攻击框架。然后,我们类比补丁优化与常规模型优化,提出了一系列的自集成方法的输入数据,攻击模型,和对抗补丁,有效地利用有限的信息,防止补丁过拟合。实验结果表明,该框架可以应用于多种经典的基础攻击方法(例如,PGD和MIM),以大大提高优化补丁在多个主流检测器上的黑盒可传输性,同时提高白盒性能。我们的代码可在https://github.com/VDIGPKU/T-SEA上获得。

英文摘要:

Compared to query-based black-box attacks, transfer-based black-box attacks do not require any information of the attacked models, which ensures their secrecy. However, most existing transfer-based approaches rely on ensembling multiple models to boost the attack transferability, which is time- and resource-intensive, not to mention the difficulty of obtaining diverse models on the same task. To address this limitation, in this work, we focus on the single-model transfer-based black-box attack on object detection, utilizing only one model to achieve a high-transferability adversarial attack on multiple black-box detectors. Specifically, we first make observations on the patch optimization process of the existing method and propose an enhanced attack framework by slightly adjusting its training strategies. Then, we analogize patch optimization with regular model optimization, proposing a series of self-ensemble approaches on the input data, the attacked model, and the adversarial patch to efficiently make use of the limited information and prevent the patch from overfitting. The experimental results show that the proposed framework can be applied with multiple classical base attack methods (e.g., PGD and MIM) to greatly improve the black-box transferability of the well-optimized patch on multiple mainstream detectors, meanwhile boosting white-box performance. Our code is available at https://github.com/VDIGPKU/T-SEA.

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。

↑