禁忌陷阱:敌对样本的行为检测
The Taboo Trap: Behavioural Detection of Adversarial Samples
摘要:
深度神经网络(DNN)已经成为解决各种问题的强大工具。然而,最近的研究发现,越来越多的对抗性样本可以欺骗它们。大多数现有的对抗对抗性攻击的检测机制都会带来巨大的成本,要么使用额外的分类器来发现对抗性样本,要么需要重新构建DNN。在本文中,我们介绍了一种新的防御。我们对DNN进行训练,以便只要它按照我们期望的输入类型工作,它的行为就会受到约束,因为某些行为是禁忌的。如果它暴露在对抗性样本中,它们往往会引起一种禁忌行为,这是我们可以检测到的。禁忌既微妙又多样,因此它们的选择可以编码和隐藏信息。系统的安全性不应该依赖于其设计的模糊性,而是依赖于某些变量(密钥),这些变量在实现之间可能不同,并在必要时进行更改,这是一个公认的设计原则。我们讨论如何禁忌可以用来装备一个分类器,这样一个关键,以及如何调整密钥机制,以各种能力的对手。我们评估了原型针对各种攻击的性能,并展示了我们的简单防御如何在零运行时计算开销的情况下大规模防御廉价攻击,使其成为物联网设备的合适防御方法。
英文摘要:
Deep Neural Networks (DNNs) have become a powerful toolfor a wide range of problems. Yet recent work has found an increasing variety of adversarial samplesthat can fool them. Most existing detection mechanisms against adversarial attacksimpose significant costs, either by using additional classifiers to spot adversarial samples, or by requiring the DNN to be restructured. In this paper, we introduce a novel defence. We train our DNN so that, as long as it is workingas intended on the kind of inputs we expect, its behavior is constrained, in that some set of behaviors are taboo. If it is exposed to adversarial samples, they will often cause a taboo behavior, which we can detect. Taboos can be both subtle and diverse, so their choice can encode and hide information. It is a well-established design principle that the security of a system should not depend on the obscurity of its design, but on some variable (the key) which can differ between implementations and bechanged as necessary. We discuss how taboos can be used to equip a classifier with just such a key, and how to tune the keying mechanism to adversaries of various capabilities. We evaluate the performance of a prototype against a wide range of attacks and show how our simple defense can defend against cheap attacks at scale with zero run-time computation overhead, making it a suitable defense method for IoT devices.
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。