arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.14580cs.CVcs.CRcs.LG
收藏

物理世界中针对深度学习系统的后门攻击

Backdoor Attacks Against Deep Learning Systems in the Physical World

University of Chicago(芝加哥大学)

Emily Wenger, Josephine Passananti, Arjun Bhagoji, Yuanshun Yao, Haitao Zheng, Ben Y. Zhao

摘要:

后门攻击将隐藏的恶意行为嵌入到深度学习模型中,仅激活并导致包含特定触发器的模型输入的错误分类。然而,现有的关于后门攻击和防御的工作主要集中在使用数字生成的模式作为触发器的数字攻击上。一个关键的问题仍然没有答案:后门攻击能否成功使用物理对象作为触发器,从而使它们成为现实世界中对深度学习系统的可信威胁?我们进行了详细的实证研究,以探索这个问题的面部识别,一个关键的深度学习任务。使用七个物理对象作为触发器,我们收集了一个自定义数据集的3205图像的10名志愿者,并使用它来研究物理后门攻击的可行性在各种现实世界的条件下。我们的研究揭示了两个关键发现。首先,物理后门攻击可以非常成功,如果它们被仔细配置以克服物理对象施加的约束。特别是,成功触发器的放置在很大程度上受到目标模型对关键面部特征的依赖性的限制。第二,当今针对(数字)后门的四种最先进的防御措施对物理后门无效,因为物理对象的使用打破了用于构建这些防御的核心假设。我们的研究证实,(物理)后门攻击不是一个假设的现象,而是对关键的分类任务构成了严重的现实威胁。我们需要新的、更强大的防御手段来抵御物理世界中的后门。

英文摘要:

Backdoor attacks embed hidden malicious behaviors into deep learning models, which only activate and cause misclassifications on model inputs containing a specific trigger. Existing works on backdoor attacks and defenses, however, mostly focus on digital attacks that use digitally generated patterns as triggers. A critical question remains unanswered: can backdoor attacks succeed using physical objects as triggers, thus making them a credible threat against deep learning systems in the real world? We conduct a detailed empirical study to explore this question for facial recognition, a critical deep learning task. Using seven physical objects as triggers, we collect a custom dataset of 3205 images of ten volunteers and use it to study the feasibility of physical backdoor attacks under a variety of real-world conditions. Our study reveals two key findings. First, physical backdoor attacks can be highly successful if they are carefully configured to overcome the constraints imposed by physical objects. In particular, the placement of successful triggers is largely constrained by the target model's dependence on key facial features. Second, four of today's state-of-the-art defenses against (digital) backdoors are ineffective against physical backdoors, because the use of physical objects breaks core assumptions used to construct these defenses. Our study confirms that (physical) backdoor attacks are not a hypothetical phenomenon but rather pose a serious real-world threat to critical classification tasks. We need new and more robust defenses against backdoors in the physical 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。

↑