https://scholars.lib.ntu.edu.tw/handle/123456789/580904
標題: | Defense Against Adversarial Attacks on Spoofing Countermeasures of ASV | 作者: | Wu H Liu S Meng H HUNG-YI LEE |
關鍵字: | Network security; Speech communication; Speech recognition; Anti-spoofing; Automatic speaker verification; Malicious adversaries; Passive defense; Proactive defense; Spatial smoothing; Audio signal processing | 公開日期: | 2020 | 卷: | 2020-May | 起(迄)頁: | 6564-6568 | 來源出版物: | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings | 摘要: | Various forefront countermeasure methods for automatic speaker verification (ASV) with considerable performance in anti-spoofing are proposed in the ASVspoof 2019 challenge. However, previous work has shown that countermeasure models are vulnerable to adversarial examples indistinguishable from natural data. A good countermeasure model should not only be robust against spoofing audio, including synthetic, converted, and replayed audios; but counteract deliberately generated examples by malicious adversaries. In this work, we introduce a passive defense method, spatial smoothing, and a proactive defense method, adversarial training, to mitigate the vulnerability of ASV spoofing countermeasure models against adversarial examples. This paper is among the first to use defense methods to improve the robustness of ASV spoofing countermeasure models under adversarial attacks. The experimental results show that these two defense methods positively help spoofing countermeasure models counter adversarial examples. ? 2020 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85089234616&doi=10.1109%2fICASSP40776.2020.9053643&partnerID=40&md5=b3761fdd525ea08a8cad4e3b0276be33 https://scholars.lib.ntu.edu.tw/handle/123456789/580904 |
ISSN: | 15206149 | DOI: | 10.1109/ICASSP40776.2020.9053643 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。