Adversarial Attack and Defense on Deep Neural Network-Based Voice Processing Systems: An Overview

Applied Sciences

Sheng Li¹  Xiaojiao Chen²  Hao Huang² 

[1] National Institute of Information and Communications Technology, Kyoto 619-0288, Japan;School of Information Science and Engineering, Xinjiang University, Urumqi 830046, China;

关键词: adversarial attack;    adversarial example;    adversarial defense;    speaker recognition;    speech recognition;   

DOI  :  10.3390/app11188450

来源: DOAJ

【 摘 要 】

Voice Processing Systems (VPSes), now widely deployed, have become deeply involved in people’s daily lives, helping drive the car, unlock the smartphone, make online purchases, etc. Unfortunately, recent research has shown that those systems based on deep neural networks are vulnerable to adversarial examples, which attract significant attention to VPS security. This review presents a detailed introduction to the background knowledge of adversarial attacks, including the generation of adversarial examples, psychoacoustic models, and evaluation indicators. Then we provide a concise introduction to defense methods against adversarial attacks. Finally, we propose a systematic classification of adversarial attacks and defense methods, with which we hope to provide a better understanding of the classification and structure for beginners in this field.

【 授权许可】

Unknown