DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery Clues

Page view(s)
96
Checked on Jun 07, 2024
DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery Clues
Title:
DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery Clues
Journal Title:
Proceedings of the 31st ACM International Conference on Multimedia
Keywords:
Publication Date:
27 October 2023
Citation:
Pan, K., Yin, Y., Wei, Y., Lin, F., Ba, Z., Liu, Z., Wang, Z., Cavallaro, L., & Ren, K. (2023). DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery Clues. Proceedings of the 31st ACM International Conference on Multimedia. https://doi.org/10.1145/3581783.3612377
Abstract:
The malicious use and widespread dissemination of deepfake pose a significant crisis of trust. Current deepfake detection models can generally recognize forgery images by training on a large dataset. However, the accuracy of detection models degrades significantly on images generated by new deepfake methods due to the difference in data distribution. To tackle this issue, we present a novel incremental learning framework that improves the generalization of deepfake detection models by continual learning from a small number of new samples. To cope with different data distributions, we propose to learn a domain-invariant representation based on supervised contrastive learning, preventing overfit to the insufficient new data. To mitigate catastrophic forgetting, we regularize our model in both feature-level and label-level based on a multi-perspective knowledge distillation approach. Finally, we propose to select both central and hard representative samples to update the replay set, which is beneficial for both domain-invariant representation learning and rehearsal-based knowledge preserving. We conduct extensive experiments on four benchmark datasets, obtaining the new state-of-the-art average forgetting rate of 7.01 and average accuracy of 85.49 on FF++, DFDC-P, DFD, and CDF2. Our code is released at https://github.com/DeepFakeIL/DFIL.
License type:
Publisher Copyright
Funding Info:
This work is partially supported by the National Key R&D Program of China (2020AAA0107700), the National Natural Science Foundation of China (62172359) and the Key R&D Program of Zhejiang Province (No.2023C01217).
Description:
© Author | ACM 2023. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of the 31st ACM International Conference on Multimedia, http://dx.doi.org/10.1145/3581783.3612377
ISBN:
979-8-4007-0108-5/23/10
Files uploaded:

File Size Format Action
dfil.pdf 2.12 MB PDF Open