Deep learning models have been widely used in commercial acoustic systems in recent years. However, adversarial audio examples can cause abnormal behaviors for those acoustic systems, while being hard for humans to perceive. Various methods, such as transformation-based defenses and adversarial training, have been proposed to protect acoustic systems from adversarial attacks, but they are less effective against adaptive attacks. Furthermore, directly applying the methods from the image domain can lead to suboptimal results because of the unique properties of audio data. In this paper, we propose an adversarial purification-based defense pipeline, AudioPure, for acoustic systems via off-the-shelf diffusion models. Taking advantage of the strong generation ability of diffusion models, AudioPure first adds a small amount of noise to the adversarial audio and then runs the reverse sampling step to purify the noisy audio and recover clean audio. AudioPure is a plug-and-play method that can be directly applied to any pretrained classifier without any fine-tuning or re-training. We conduct extensive experiments on speech command recognition task to evaluate the robustness of AudioPure. Our method is effective against diverse adversarial attacks (e.g. $\mathcal{L}_2$ or $\mathcal{L}_\infty$-norm). It outperforms the existing methods under both strong adaptive white-box and black-box attacks bounded by $\mathcal{L}_2$ or $\mathcal{L}_\infty$-norm (up to +20\% in robust accuracy). Besides, we also evaluate the certified robustness for perturbations bounded by $\mathcal{L}_2$-norm via randomized smoothing. Our pipeline achieves a higher certified accuracy than baselines.
翻译:近些年来,商业声学系统广泛使用了深层次学习模型。 但是, 对抗性音频示例可以给这些声学系统造成异常行为, 而人类很难感知。 各种方法, 如变换防御和对抗训练, 被提议保护声学系统免受对抗性攻击, 但对于适应性攻击, 效果不那么好。 此外, 直接应用图像域的方法可以导致低于最佳效果, 因为音频数据具有独特的特性。 在本文中, 我们提议通过现成的准确性传播模型为声学系统提供一个对抗性净化防御管道( AudioPure ) 。 利用强大的扩散模型生成能力, 音频Pure首先为对辩论性声学系统增加少量噪音, 然后进行反向采样步骤, 净化噪音音频声学和清洁音频攻击。 音频调是直接应用于任何未受过训练的精选的精选精选精选精选精选精选精选精选的精选精选方法, 我们用声学感学确认任务来评价音学精选的精选精选精选精选能力。 我们的方法, 也有效对付多种反调性反调性的调性调性调性攻击, 基基调的调 美元 基调 基调 基调制 。</s>