Abstract
Continual audio deepfake detection requires learning newly emerging deepfake methods while retaining discrimination of previously encountered speech. Existing dataset-incremental evaluation changes both real-speech domains and deepfake mechanisms, making their effects difficult to distinguish. We construct five task organizations over identical training, development, and evaluation pools to study these factors under a controlled sample budget. Our proposed Real-Anchored Mechanism-Incremental (RAMI) protocol reflects the practical setting in which available real speech provides a recurring mixed-domain reference while new deepfake mechanisms arrive incrementally. We further propose RF-Prompt, an asymmetric continual prompt-learning method that preserves reusable real-speech knowledge through a shared real prompt and expands mechanism-specific knowledge through inherited fake experts with orthogonal residuals. Input-adaptive soft fusion combines the accumulated experts into a fixed number of injected tokens without requiring task identity at inference. On RAMI, RF-Prompt achieves 10.110% average EER and 10.370% pooled EER, outperforming all evaluated continual-learning baselines. Across the five controlled protocols, RAMI yields the lowest common-average and pooled EER. Component ablations, limited-data experiments, and cross-backbone evaluations further validate the proposed design.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Xie, Y., Guo, X., Wang, X., Qin, S., Li, S., & Lee, K. A. (2026). Learning as Deepfakes Evolve: RF-Prompt for Continual Audio Deepfake Detection. https://omanscience.com/en/articles/learning-as-deepfakes-evolve-rf-prompt-for-continual-audio-deepfake-detection
MLA 9
Xie, Yuankun, et al. "Learning as Deepfakes Evolve: RF-Prompt for Continual Audio Deepfake Detection." https://omanscience.com/en/articles/learning-as-deepfakes-evolve-rf-prompt-for-continual-audio-deepfake-detection.
Chicago (author–date)
Xie, Yuankun, Xiaoxuan Guo, Xiaopeng Wang, Siqing Qin, Shaole Li, and Kong Aik Lee. 2026. "Learning as Deepfakes Evolve: RF-Prompt for Continual Audio Deepfake Detection." https://omanscience.com/en/articles/learning-as-deepfakes-evolve-rf-prompt-for-continual-audio-deepfake-detection.
Harvard
Xie, Y., Guo, X., Wang, X., Qin, S., Li, S. and Lee, K. A. (2026) 'Learning as Deepfakes Evolve: RF-Prompt for Continual Audio Deepfake Detection', Available at: https://omanscience.com/en/articles/learning-as-deepfakes-evolve-rf-prompt-for-continual-audio-deepfake-detection.
Vancouver
Xie Y, Guo X, Wang X, Qin S, Li S, Lee KA. Learning as Deepfakes Evolve: RF-Prompt for Continual Audio Deepfake Detection. https://omanscience.com/en/articles/learning-as-deepfakes-evolve-rf-prompt-for-continual-audio-deepfake-detection
IEEE
Y. Xie, X. Guo, X. Wang, S. Qin, S. Li, and K. A. Lee, "Learning as Deepfakes Evolve: RF-Prompt for Continual Audio Deepfake Detection," https://omanscience.com/en/articles/learning-as-deepfakes-evolve-rf-prompt-for-continual-audio-deepfake-detection.