Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; the references it cites are not checked yet.

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

Open access
Pan, Kun, Yin, Yifang, Wei, Yao, Lin, Feng, Ba, Zhongjie, Liu, Zhenguang, Wang, Zhibo, Cavallaro, Lorenzo, Ren, Kui · 2023 · Proceedings of the 31st ACM International Conference on Multimedia

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 \textcolorblue https://github.com/DeepFakeIL/DFIL.

Overview

Integrity signals

Registry

Crossref · 10.1145/3581783.3612377

Cites

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

The citation lists are queued

They are fetched later and appear here then.

References 67 · Cited by 37

Research works printed but not linked: 13

  1. Arslan Chaudhry, Marcus Rohrbach, Mohamed Elhoseiny, Thalaiyasingam Ajanthan, Puneet K Dokania, Philip HS Torr, and Marc'Aurelio Ranzato. On tiny episodic memories in continual learning. arXiv preprint arXiv:1902.10486, 2019. · arXiv
  2. Aidan Clark, Jeff Donahue, and Karen Simonyan. Adversarial video generation on complex datasets. arXiv preprint arXiv:1907.06571, 2019. · arXiv
  3. Brian Dolhansky, Russ Howes, Ben Pflaum, Nicole Baram, and Cristian Canton Ferrer. The deepfake detection challenge (dfdc) preview dataset. arXiv preprint arXiv:1910.08854, 2019. · arXiv
  4. Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, 2015. · arXiv
  5. Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. Supervised contrastive learning. Advances in neural information processing systems, 33:18661--18673, 2020.
  6. Lingzhi Li, Jianmin Bao, Hao Yang, Dong Chen, and Fang Wen. Faceshifter: Towards high fidelity and occlusion aware face swapping. arXiv preprint arXiv:1912.13457, 2019. · arXiv
  7. Zhenguang Liu, Zepeng Wang, Luming Zhang, Rajiv Ratn Shah, Yingjie Xia, Yi Yang, and Xuelong Li. Fastshrinkage: Perceptually-aware retargeting toward mobile platforms. In ACM MM, pages 501--509, 2017.
  8. Momo. Zaoapp. https://zao.en.softonic.com/android, 2020.
  9. Andrei A Rusu, Neil C Rabinowitz, Guillaume Desjardins, Hubert Soyer, James Kirkpatrick, Koray Kavukcuoglu, Razvan Pascanu, and Raia Hadsell. Progressive neural networks. arXiv preprint arXiv:1606.04671, 2016. · arXiv
  10. Hanul Shin, Jung Kwon Lee, Jaehong Kim, and Jiwon Kim. Continual learning with deep generative replay. Advances in neural information processing systems, 30, 2017.
  11. Yuhan Wang, Xu Chen, Junwei Zhu, Wenqing Chu, Ying Tai, Chengjie Wang, Jilin Li, Yongjian Wu, Feiyue Huang, and Rongrong Ji. Hififace: 3d shape and semantic prior guided high fidelity face swapping. arXiv preprint arXiv:2106.09965, 2021. · arXiv
  12. Yuheng Yang, Haipeng Chen, Zhenguang Liu, Yingda Lyu, Beibei Zhang, Shuang Wu, Zhibo Wang, and Kui Ren. Action recognition with multi-stream motion modeling and mutual information maximization. arXiv preprint arXiv:2306.07576, 2023. · arXiv
  13. 10.1145/3474085.3475272 · DOI

Metadata

Authors
Pan, K., Yin, Y., Wei, Y., Lin, F., Ba, Z., Liu, Z., Wang, Z., Cavallaro, L., & Ren, K.
Affiliations
  • Zhejiang University (CN)
  • Agency for Science, Technology and Research (SG)
  • Zhejiang University, Hangzhou, China
  • University College London (GB)
Venue
Proceedings of the 31st ACM International Conference on Multimedia
Publisher
ACM
Published
2023-10-26
Pages
8035-8046
OpenAlex
W4388189737
Cited by
37
References
67
Citations by year
2026: 13 · 2025: 11 · 2024: 12 · 2023: 1
FWCI
3.96
Type
conference paper
Language
en
Open access
Locations
  • ACM International Conference on Multimedia (ACM MM) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • UCL Discovery (University College London) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • National Key R&D Program of China (2020AAA0107700)
  • National Natural Science Foundation of China (62172359)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
Keywords
deepfake detection, incremental learning, continual learning, catastrophic forgetting, domain-invariant features, supervised contrastive learning, knowledge distillation, hard sample selection, distribution shift, forgery detection

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: DFIL: Deepfake Incremental Learning by Exploiting Domain-invariant Forgery Clues. https://app.cochat.ai/papers/10.1145/3581783.3612377
The paper
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

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.