https://scholars.lib.ntu.edu.tw/handle/123456789/607158
Title: | Adversarial Defense for Automatic Speaker Verification by Cascaded Self-Supervised Learning Models | Authors: | Wu H Li X Liu A.T Wu Z Meng H HUNG-YI LEE |
Keywords: | Adversarial attack;Adversarial defense;Automatic speaker verification;Self-supervised learning;Network security;Safety engineering;Signal processing;Speech recognition;Supervised learning;Biometric identifications;Core technology;Pre-training;Safety critical applications;Learning systems | Issue Date: | 2021 | Journal Volume: | 2021-June | Start page/Pages: | 6718-6722 | Source: | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings | Abstract: | Automatic speaker verification (ASV) is one of the core technologies in biometric identification. With the ubiquitous usage of ASV systems in safety-critical applications, more and more malicious attackers attempt to launch adversarial attacks at ASV systems. In the midst of the arms race between attack and defense in ASV, how to effectively improve the robustness of ASV against adversarial attacks remains an open question. We note that the self-supervised learning models possess the ability to mitigate superficial perturbations in the input after pretraining. Hence, with the goal of effective defense in ASV against adversarial attacks, we propose a standard and attack-agnostic method based on cascaded self-supervised learning models to purify the adversarial perturbations. Experimental results demonstrate that the proposed method achieves effective defense performance and can successfully counter adversarial attacks in scenarios where attackers may either be aware or unaware of the self-supervised learning models. ?2021 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85111428848&doi=10.1109%2fICASSP39728.2021.9413737&partnerID=40&md5=ee129cec8a1eee3bbe5d33596f529990 https://scholars.lib.ntu.edu.tw/handle/123456789/607158 |
ISSN: | 15206149 | DOI: | 10.1109/ICASSP39728.2021.9413737 |
Appears in Collections: | 電機工程學系 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.