Rehearsal with Auxiliary-Informed Sampling for Audio Deepfake Detection
Open accessThe DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 33
- [1][1] Z. Wu, R. K. Das, J. Yang, and H. Li, 'Light convolutional neural network with feature genuinization for detection of synthetic speech attacks,' in INTERSPEECH , 2020. -
- [2][2] X. Liu, M. Liu, L. Wang, K. A. Lee, H. Zhang, and J. Dang, 'Leveraging positional-related local-global dependency for synthetic speech detection,' in ICASSP , 2023. -
- [3][3] J.-w. Jung, H.-S. Heo, H. Tak, H.-j. Shim, J. S. Chung, B.-J. Lee, H.-J. Yu, and N. Evans, 'Aasist: Audio anti-spoofing using integrated spectro-temporal graph attention networks,' in ICASSP , 2022. -
- [4][4] H. Tak, M. Todisco, X. Wang, J.-w. Jung, J. Yamagishi, and N. Evans, 'Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation,' in Proc. The Speaker and Language Recognition Workshop (Odyssey) , 2022. -
- [5][5] X. Zhang, J. Yi, C. Wang, C. Y. Zhang, S. Zeng, and J. Tao, 'What to remember: Self-adaptive continual learning for audio deepfake detection,' in Proceedings of the AAAI Conference on Artificial Intelligence , vol. 38, no. 17, 2024, pp. 19 569-19 577. -
- [6][6] X. Zhang, J. Yi, J. Tao, C. Wang, and C. Y. Zhang, 'Do you remember? overcoming catastrophic forgetting for fake audio detection,' in International Conference on Machine Learning . PMLR, 2023, pp. 41 819-41 831. -
- [7][7] Z. Wang, E. Yang, L. Shen, and H. Huang, 'A comprehensive survey of forgetting in deep learning beyond continual learning,' IEEE Transactions on Pattern Analysis and Machine Intelligence , 2024. -
- [8][8] L. Wang, X. Zhang, H. Su, and J. Zhu, 'A comprehensive survey of continual learning: theory, method and application,' IEEE Transactions on Pattern Analysis and Machine Intelligence , 2024. -
- [9][9] D. Salvi, V. Negroni, L. Bondi, P. Bestagini, and S. Tubaro, 'Freeze and learn: Continual learning with selective freezing for speech deepfake detection,' in ICASSP , 2025. -
- [10][10] F. G. Febrinanto, F. Xia, K. Moore, C. Thapa, and C. Aggarwal, 'Graph lifelong learning: A survey,' IEEE Computational Intelligence Magazine , vol. 18, no. 1, pp. 32-51, 2023. -
- [11][11] Y.-C. Yu, C.-P. Huang, J.-J. Chen, K.-P. Chang, Y.-H. Lai, F.-E. Yang, and Y.-C. F. Wang, 'Select and distill: Selective dual-teacher knowledge transfer for continual learning on visionlanguage models,' in European Conference on Computer Vision . Springer, 2025, pp. 219-236. -
- [13][13] Y. Chen, J. Yi, C. Fan, J. Tao, Y. Ren, S. Zeng, C. Y. Zhang, X. Yan, H. Gu, J. Xue et al. , 'Region-based optimization in continual learning for audio deepfake detection,' in Proceedings of the AAAI Conference on Artificial Intelligence , vol. 39, no. 22, 2025, pp. 23 651-23 659. -
- [14][14] X. Chen, W. Lu, R. Zhang, J. Xu, X. Lu, L. Zhang, and J. Wei, 'Continual unsupervised domain adaptation for audio deepfake detection,' in ICASSP , 2025. -
- [15][15] A. Krutsylo, 'The inter-batch diversity of samples in experience replay for continual learning,' in Proceedings of the AAAI Conference on Artificial Intelligence , vol. 38, no. 21, 2024, pp. 23 39523 396. -
- [16][16] D. Rolnick, A. Ahuja, J. Schwarz, T. Lillicrap, and G. Wayne, 'Experience replay for continual learning,' Advances in neural information processing systems , vol. 32, 2019. -
- [17][17] L. Caccia, R. Aljundi, N. Asadi, T. Tuytelaars, J. Pineau, and E. Belilovsky, 'New insights on reducing abrupt representation change in online continual learning,' in International Conference on Learning Representations , 2022. -
- [18][18] L. Hanmo, D. Shimin, L. Haoyang, L. Shuangyin, C. Lei, and Z. Xiaofang, 'Effective data selection and replay for unsupervised continual learning,' in 2024 IEEE 40th International Conference on Data Engineering (ICDE) . IEEE, 2024, pp. 1449-1463. -
- [19][19] D. Rolnick, A. Ahuja, J. Schwarz, T. Lillicrap, and G. Wayne, 'Experience replay for continual learning,' Advances in neural information processing systems , vol. 32, 2019. -
- [20][20] S.-A. Rebuffi, A. Kolesnikov, G. Sperl, and C. H. Lampert, 'icarl: Incremental classifier and representation learning,' in Proceedings of the IEEE conference on Computer Vision and Pattern Recognition , 2017, pp. 2001-2010. -
- [21][21] R. Aljundi, M. Lin, B. Goujaud, and Y. Bengio, 'Gradient based sample selection for online continual learning,' Advances in neural information processing systems , vol. 32, 2019. -
- [22][22] R. Aljundi, E. Belilovsky, T. Tuytelaars, L. Charlin, M. Caccia, M. Lin, and L. Page-Caccia, 'Online continual learning with maximal interfered retrieval,' Advances in neural information processing systems , vol. 32, 2019. -
- [23][23] A. Chrysakis and M.-F. Moens, 'Online continual learning from imbalanced data,' in International Conference on Machine Learning . PMLR, 2020, pp. 1952-1961. -
- [24][24] S. Liu, A. Davison, and E. Johns, 'Self-supervised generalisation with meta auxiliary learning,' Advances in Neural Information Processing Systems , vol. 32, 2019. -
- [25][25] C. Ding, Z. Lu, S. Wang, R. Cheng, and V. N. Boddeti, 'Mitigating task interference in multi-task learning via explicit task routing with non-learnable primitives,' in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2023, pp. 7756-7765. -
- [26][26] A. Baevski, A. Babu, W.-N. Hsu, and M. Auli, 'Efficient selfsupervised learning with contextualized target representations for vision, speech and language,' in International Conference on Machine Learning . PMLR, 2023, pp. 1416-1429. -
- [27][27] M. Todisco, X. Wang, V. Vestman, M. Sahidullah, H. Delgado, A. Nautsch, J. Yamagishi, N. Evans, T. Kinnunen, and K. A. Lee, 'Asvspoof 2019: Future horizons in spoofed and fake audio detection,' in INTERSPEECH , 2019. -
- [28][28] N. M. M¨ uller, P. Czempin, F. Dieckmann, A. Froghyar, and K. B¨ ottinger, 'Does audio deepfake detection generalize?' in INTERSPEECH , 2022. -
- [29][29] H. Ma, J. Yi, C. Wang, X. Yan, J. Tao, T. Wang, S. Wang, and R. Fu, 'Cfad: A chinese dataset for fake audio detection,' Speech Communication , vol. 164, p. 103122, 2024. -
- [30][30] A. Baevski, Y. Zhou, A. Mohamed, and M. Auli, 'wav2vec 2.0: A framework for self-supervised learning of speech representations,' NeurIPS , 2020. -
- [31][31] J.-w. Jung, H.-S. Heo, H. Tak, H.-j. Shim, J. S. Chung, B.-J. Lee, H.-J. Yu, and N. Evans, 'Aasist: Audio anti-spoofing using integrated spectro-temporal graph attention networks,' in ICASSP , 2022. -
- [32][32] J. Kirkpatrick, R. Pascanu, N. Rabinowitz, J. Veness, G. Desjardins, A. A. Rusu, K. Milan, J. Quan, T. Ramalho, A. GrabskaBarwinska et al. , 'Overcoming catastrophic forgetting in neural networks,' Proceedings of the national academy of sciences , vol. 114, no. 13, pp. 3521-3526, 2017. -
- [33][33] Z. Li and D. Hoiem, 'Learning without forgetting,' IEEE transactions on pattern analysis and machine intelligence , vol. 40, no. 12, pp. 2935-2947, 2017. -
- [34][34] G. Zeng, Y. Chen, B. Cui, and S. Yu, 'Continual learning of context-dependent processing in neural networks,' Nature Machine Intelligence , vol. 1, no. 8, pp. 364-372, 2019.
Cited by
Nguyen-Le, H.-H., Tran, V.-T., Nguyen, D.-T., & Le-Khac, N.-A. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11608-4 · Cited by 28
Jeswani, U., & Priyadharshini, S. (2026) · International Conference on Innovative Trends in Information Technology (ICITIIT) · doi:10.1109/icitiit68860.2026.11499629
Metadata
- Authors
- Febrinanto, F. G., Moore, K., Thapa, C., Ma, J., Saikrishna, V., & Xia, F.
- Venue
- Interspeech 2025
- Publisher
- ISCA
- Published
- 2025-08-17
- Pages
- 5358-5362
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W4415433058
- Semantic Scholar
- 71065a9438527ccc6dedb860f5a502230ef273ec
- Cited by
- 1
- References
- 0
- Citations by year
- 2026: 1
- FWCI
- 0.70
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Interspeech (USB) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Keywords
- audio deepfake detection, forgetting, audio forensics, adversarial attacks
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.