Adversarial examples seem to be inevitable. These specifically crafted inputs allow attackers to arbitrarily manipulate machine learning systems. Even worse, they often seem harmless to human observers. In our digital society, this poses a significant threat. For example, Automatic Speech Recognition (ASR) systems, which serve as hands-free interfaces to many kinds of systems, can be attacked with inputs incomprehensible for human listeners. The research community has unsuccessfully tried several approaches to tackle this problem. In this paper we propose a different perspective: We accept the presence of adversarial examples against ASR systems, but we require them to be perceivable by human listeners. By applying the principles of psychoacoustics, we can remove semantically irrelevant information from the ASR input and train a model that resembles human perception more closely. We implement our idea in a tool named DOMPTEUR and demonstrate that our augmented system, in contrast to an unmodified baseline, successfully focuses on perceptible ranges of the input signal. This change forces adversarial examples into the audible range, while using minimal computational overhead and preserving benign performance. To evaluate our approach, we construct an adaptive attacker that actively tries to avoid our augmentations and demonstrate that adversarial examples from this attacker remain clearly perceivable. Finally, we substantiate our claims by performing a hearing test with crowd-sourced human listeners.
翻译:反versarial 实例似乎不可避免。 这些具体设计的投入让攻击者任意操纵机器学习系统。 更糟糕的是, 它们似乎对人类观察者来说是无害的。 在我们的数字社会中, 这构成了巨大的威胁。 例如, 自动语音识别系统(ASR)作为许多类型的系统的无手界面, 可以用人类听众无法理解的投入来攻击。 研究界尝试了多种方法来解决这一问题, 但没有成功。 在本文中, 我们提出了一个不同的观点: 我们接受针对 ASR 系统的对抗性范例, 但我们要求它们为人类听众所接受。 通过应用心理学学原理, 我们可以删除 ASR 输入的不相干的信息, 并训练一种更接近人类感知的模型。 我们用名为 DOMPTEUR 的工具来实施我们的想法, 并展示我们强化的系统, 与未改变的基线相比, 成功地侧重于输入信号的可辨辨识范围。 我们接受的对抗性范例在可辨识的范围中,, 我们使用极小的计算顶部和保持友好性的表现。 为了评估我们的方法, 我们从ADiral advieworal ex ex ex subal subaltraction view view view view view view we view view view view view view view view view view us views