EUVIMEDEUVIMED entdecken
Crossref

Region-Based Optimization in Continual Learning for Audio Deepfake Detection

Yujie Chen, Jiangyan Yi, Cunhang Fan, Jianhua Tao, Yong Ren, Siding Zeng, Chu Yuan Zhang, Xinrui Yan, Hao Gu, Jun Xue, Chenglong Wang, Zhao Lv und 1 weitere

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (22) · 23651-23659

DOI: 10.1609/aaai.v39i22.34535 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Yujie Chen und 12 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Rapid advancements in speech synthesis and voice conversion bring convenience but also new security risks, creating an urgent need for effective audio deepfake detection. Although current models perform well, their effectiveness diminishes when confronted with the diverse and evolving nature of real-world deepfakes. To address this issue, we propose a continual learning method named Region-Based Optimization (RegO) for audio deepfake detection. Specifically, we use the Fisher information matrix to measure important neuron regions for real and fake audio detection, dividing them into four regions. First, we directly fine-tune the less important regions to quickly adapt to new tasks. Next, we apply gradient optimization in parallel for regions important only to real audio detection, and in orthogonal directions for regions important only to fake audio detection. For regions that are important to both, we use sample proportion-based adaptive gradient optimization. This region-adaptive optimization ensures an appropriate trade-off between memory stability and learning plasticity. Additionally, to address the increase of redundant neurons from old tasks, we further introduce the Ebbinghaus forgetting mechanism to release them, thereby promoting the model’s ability to learn more generalized discriminative features. Experimental results show our method achieves a 21.3 percent improvement in EER over the state-of-the-art continual learning approach RWM for audio deepfake detection. Moreover, the effectiveness of RegO extends beyond the audio deepfake detection domain, showing potential significance in other tasks, such as image recognition.

Zitieren

APA

Chen, Y., Yi, J., Fan, C., Tao, J., Ren, Y., Zeng, S., Zhang, C. Y., Yan, X., Gu, H., Xue, J., Wang, C., Lv, Z., & Zhang, X. (2025). Region-Based Optimization in Continual Learning for Audio Deepfake Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 39(22), 23651-23659. https://doi.org/10.1609/aaai.v39i22.34535

Vancouver

Chen Y, Yi J, Fan C, Tao J, Ren Y, Zeng S, et al. Region-Based Optimization in Continual Learning for Audio Deepfake Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(22):23651-23659. doi:10.1609/aaai.v39i22.34535

BibTeX
@article{Chen2025,
  author = {Chen, Yujie and Yi, Jiangyan and Fan, Cunhang and Tao, Jianhua and Ren, Yong and Zeng, Siding and Zhang, Chu Yuan and Yan, Xinrui and Gu, Hao and Xue, Jun and Wang, Chenglong and Lv, Zhao and Zhang, Xiaohui},
  title = {Region-Based Optimization in Continual Learning for Audio Deepfake Detection},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {22},
  pages = {23651--23659},
  doi = {10.1609/aaai.v39i22.34535}
}
Kostenlos starten →