一句话：提出可跨 ASR 迁移的黑盒对抗攻击技术，并给出解释方法以理解 ASR 易受攻击的原因。
自动语音识别（ASR）广泛用于语音导航与家电语音控制，其计算核心是深度神经网络（DNN），而 DNN 已被证明容易受到对抗扰动影响，并存在不良偏见与伦理问题。为评估 ASR 的安全性，本文提出黑盒（与具体 DNN 无关）的对抗攻击生成技术，所生成的攻击可以在不同 ASR 之间迁移使用；这与已有工作主要关注白盒攻击形成对比——白盒攻击耗时长且缺乏可移植性。此外，为了弄清 ASR（始终处于黑盒使用场景）为何如此容易被攻击，作者还为 ASR 提供了解释方法，用以增进对系统的理解，并最终帮助建立对系统的信任。
Automatic speech recognition (ASR) models are used widely in applications for voice navigation and voice control of domestic appliances. The computational core of ASRs are Deep Neural Networks (DNNs) that have been shown to be susceptible to adversarial perturbations and exhibit unwanted biases and ethical issues. To assess the security of ASRs, we propose techniques that generate blackbox (agnostic to the DNN) adversarial attacks that are portable across ASRs. This is in contrast to existing work that focuses on whitebox attacks that are time consuming and lack portability. Apart from that, to figure out why ASRs(always blackbox) are easily attacked, we provide explanation methods on ASRs that help increase our understanding of the system and ultimately help build trust in the system.
DOI 原文 ·
@inproceedings{paperbot6964,
title = {Blackbox adversarial attacks and explanations for automatic speech recognition},
author = {Xiaoliang Wu},
booktitle = {FSE},
year = {2022},
doi = {10.1145/3540250.3558906}
}