What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (17) · 19569-19577
DOI: 10.1609/aaai.v38i17.29929 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von XiaoHui Zhang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 31-mal zitiert (Crossref).
Abstract (Originalsprache)
The rapid evolution of speech synthesis and voice conversion has raised substantial concerns due to the potential misuse of such technology, prompting a pressing need for effective audio deepfake detection mechanisms. Existing detection models have shown remarkable success in discriminating known deepfake audio, but struggle when encountering new attack types. To address this challenge, one of the emergent effective approaches is continual learning. In this paper, we propose a continual learning approach called Radian Weight Modification (RWM) for audio deepfake detection. The fundamental concept underlying RWM involves categorizing all classes into two groups: those with compact feature distributions across tasks, such as genuine audio, and those with more spread-out distributions, like various types of fake audio. These distinctions are quantified by means of the in-class cosine distance, which subsequently serves as the basis for RWM to introduce a trainable gradient modification direction for distinct data types. Experimental evaluations against mainstream continual learning methods reveal the superiority of RWM in terms of knowledge acquisition and mitigating forgetting in audio deepfake detection. Furthermore, RWM's applicability extends beyond audio deepfake detection, demonstrating its potential significance in diverse machine learning domains such as image recognition.
Zitieren
APA
Zhang, X., Yi, J., Wang, C., Zhang, C. Y., Zeng, S., & Tao, J. (2024). What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 38(17), 19569-19577. https://doi.org/10.1609/aaai.v38i17.29929
Vancouver
Zhang X, Yi J, Wang C, Zhang CY, Zeng S, Tao J. What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(17):19569-19577. doi:10.1609/aaai.v38i17.29929
BibTeX
@article{Zhang2024,
author = {Zhang, XiaoHui and Yi, Jiangyan and Wang, Chenglong and Zhang, Chu Yuan and Zeng, Siding and Tao, Jianhua},
title = {What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {17},
pages = {19569--19577},
doi = {10.1609/aaai.v38i17.29929}
}
EUVIMED