# Rehearsal with Auxiliary-Informed Sampling for Audio Deepfake Detection

arXiv: https://arxiv.org/abs/2505.24486 · HTML: https://mlsanity.com/paper/2505.24486/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 32 references that are in the map.
- First posted on arXiv 30 May 2025.

## Builds on (most cited first, 27 of 27)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Gradient based sample selection for online continual learning](https://mlsanity.com/paper/1903.08671/) (2019)
- [Online Continual Learning with Maximally Interfered Retrieval](https://mlsanity.com/paper/1908.04742/) (2019)
- [New Insights on Reducing Abrupt Representation Change in Online Continual Learning](https://mlsanity.com/paper/2104.05025/) (2021)
- [AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks](https://mlsanity.com/paper/2110.01200/) (2021)
- [Continual Learning of Context-dependent Processing in Neural Networks](https://mlsanity.com/paper/1810.01256/) (2018)
- [ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection](https://mlsanity.com/paper/1904.05441/) (2019)
- [Does Audio Deepfake Detection Generalize?](https://mlsanity.com/paper/2203.16263/) (2022)
- [Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation](https://mlsanity.com/paper/2202.12233/) (2022)
- [Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language](https://mlsanity.com/paper/2212.07525/) (2022)
- [Self-Supervised Generalisation with Meta Auxiliary Learning](https://mlsanity.com/paper/1901.08933/) (2019)
- [A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning](https://mlsanity.com/paper/2307.09218/) (2023)
- [Graph Lifelong Learning: A Survey](https://mlsanity.com/paper/2202.10688/) (2022)
- [Continual Learning for Fake Audio Detection](https://mlsanity.com/paper/2104.07286/) (2021)
- [Light Convolutional Neural Network with Feature Genuinization for Detection of Synthetic Speech Attacks](https://mlsanity.com/paper/2009.09637/) (2020)
- [Select and Distill: Selective Dual-Teacher Knowledge Transfer for Continual Learning on Vision-Language Models](https://mlsanity.com/paper/2403.09296/) (2024)
- [Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing with Non-Learnable Primitives](https://mlsanity.com/paper/2308.02066/) (2023)
- [What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection](https://mlsanity.com/paper/2312.09651/) (2023)
- [CFAD: A Chinese Dataset for Fake Audio Detection](https://mlsanity.com/paper/2207.12308/) (2022)
- [Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detection](https://mlsanity.com/paper/2308.03300/) (2023)
- [Region-Based Optimization in Continual Learning for Audio Deepfake Detection](https://mlsanity.com/paper/2412.11551/) (2024)
- [Freeze and Learn: Continual Learning with Selective Freezing for Speech Deepfake Detection](https://mlsanity.com/paper/2409.17598/) (2024)

## Abstract (arXiv)

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.