Rehearsal with Auxiliary-Informed Sampling for Audio Deepfake Detection
Preprint
Abstract
The performance of existing audio deepfake detection frameworks degrades when confronted with new deepfake attacks. Rehearsal-based continual learning (CL), which updates models using a limited set of old data samples, helps preserve prior knowledge while incorporating new information. However, existing rehearsal techniques don't effectively capture the diversity of audio characteristics, introducing bias and increasing the risk of forgetting. To address this challenge, we propose Rehearsal with Auxiliary-Informed Sampling (RAIS), a rehearsal-based CL approach for audio deepfake detection. RAIS employs a label generation network to produce auxiliary labels, guiding diverse sample selection for the memory buffer. Extensive experiments show RAIS outperforms state-of-the-art methods, achieving an average Equal Error Rate (EER) of 1.953 % across five experiences. The code is available at: https://github.com/falihgoz/RAIS.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Continual Unsupervised Domain Adaptation for Audio Deepfake Detection2025
- Freeze and Learn: Continual Learning with Selective Freezing for Speech Deepfake Detection2025
- A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
- CFAD: A Chinese dataset for fake audio detectionSpeech Communication, 2024
- A Comprehensive Survey of Continual Learning: Theory, Method and ApplicationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
- Leveraging Positional-Related Local-Global Dependency for Synthetic Speech Detection2023
- Graph Lifelong Learning: A SurveyIEEE Computational Intelligence Magazine, 2023
- AASIST: Audio Anti-Spoofing Using Integrated Spectro-Temporal Graph Attention Networks2022
- Continual learning of context-dependent processing in neural networksNature Machine Intelligence, 2019
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences, 2017