CoChat

Detection of Deepfake Videos Using Long-Distance Attention

Open access
Lu, Wei, Liu, Lingyi, Zhang, Bolin, Luo, Junwei, Zhao, Xianfeng, Zhou, Yicong, Huang, Jiwu · 2024 · IEEE Transactions on Neural Networks and Learning Systems
Cited by 72

The DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.

Abstract

With the rapid progress of deepfake techniques in recent years, facial video forgery can generate highly deceptive video content and bring severe security threats. And detection of such forgery videos is much more urgent and challenging. Most existing detection methods treat the problem as a vanilla binary classification problem. In this article, the problem is treated as a special fine-grained classification problem since the differences between fake and real faces are very subtle. It is observed that most existing face forgery methods left some common artifacts in the spatial domain and time domain, including generative defects in the spatial domain and interframe inconsistencies in the time domain. And a spatial-temporal model is proposed which has two components for capturing spatial and temporal forgery traces from a global perspective, respectively. The two components are designed using a novel long-distance attention mechanism. One component of the spatial domain is used to capture artifacts in a single frame, and the other component of the time domain is used to capture artifacts in consecutive frames. They generate attention maps in the form of patches. The attention method has a broader vision which contributes to better assembling global information and extracting local statistic information. Finally, the attention maps are used to guide the network to focus on pivotal parts of the face, just like other fine-grained classification methods. The experimental results on different public datasets demonstrate that the proposed method achieves state-of-the-art performance, and the proposed long-distance attention method can effectively capture pivotal parts for face forgery.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tnnls.2022.3233063

Cites

32 of 32 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Research works printed but not linked: 48

  1. 10.5555/2969033.2969125 · doi:10.5555/2969033.2969125
  2. 10.48550/arXiv.1312.6114 · DOI · Paper page
  3. 10.1109/TNNLS.2020.2978127 · DOI
  4. 2019, Deepfake
  5. 2019, Faceswap
  6. 10.1145/3335203.3335724 · DOI · Paper page
  7. Dang-Nguyen, Discrimination between computer generated and natural human faces based on asymmetry information, 1234
  8. 10.1109/ICPR48806.2021.9413139 · DOI
  9. 10.1109/tifs.2020.3045937 · DOI · Paper page
  10. 10.1109/ICCVW.2019.00213 · DOI · Paper page
  11. Wang, 2020, Exposing deep-faked videos by anomalous co-motion pattern detection, arXiv:2008.04848 · arXiv
  12. Hu, 2019, See better before looking closer: Weakly supervised data augmentation network for fine-grained visual classification, arXiv:1901.09891 · arXiv
  13. Agarwal, Protecting world leaders against deep fakes, 1
  14. 10.1109/TNNLS.2013.2287275 · DOI · Paper page
  15. Dosovitskiy, 2021, An image is worth 16×16 words: Transformers for image recognition at scale, arXiv:2010.11929 · arXiv
  16. Wodajo, 2021, Deepfake video detection using convolutional vision transformer, arXiv:2102.11126 · arXiv
  17. Heo, 2021, Deepfake detection scheme based on vision transformer and distillation, arXiv:2104.01353 · arXiv
  18. 10.1109/CVPR.2016.311 · DOI · Paper page
  19. 10.1109/TNNLS.2015.2506664 · DOI
  20. 10.1109/CVPR.2015.7298685 · DOI · Paper page
  21. 10.1109/tnnls.2020.3027589 · DOI
  22. 10.1109/CVPR.2016.132 · DOI · Paper page
  23. 10.1109/CVPR.2016.129 · DOI · Paper page
  24. 10.1016/j.patcog.2017.10.002 · DOI · Paper page
  25. 10.1109/CVPR.2017.476 · DOI · Paper page
  26. 10.1109/TPAMI.2019.2913372 · DOI · Paper page
  27. 10.48550/ARXIV.1706.03762 · DOI · Paper page
  28. 10.1109/CVPR46437.2021.00151 · DOI
  29. 10.1007/s11263-021-01473-9 · DOI
  30. 10.1109/TIP.2020.3016486 · DOI · Paper page
  31. Dumoulin, 2016, A guide to convolution arithmetic for deep learning, arXiv:1603.07285 · arXiv
  32. 10.1109/TNNLS.2013.2245340 · DOI
  33. 10.1109/TNNLS.2015.2464681 · DOI
  34. 10.1109/CVPR.2017.195 · DOI · Paper page
  35. 10.1109/TNNLS.2020.3007790 · DOI
  36. 10.1109/TPAMI.2015.2408359 · DOI · Paper page
  37. 10.1109/TNNLS.2017.2693221 · DOI
  38. 10.1109/TNNLS.2017.2648122 · DOI
  39. 10.1145/3306346.3323035 · DOI · Paper page
  40. King, 2009, Dlib-ml: A machine learning toolkit, J. Mach. Learn. Res., 10, 1755
  41. Tan, EfficientNet: Rethinking model scaling for convolutional neural networks, 97, 6105
  42. 10.1109/ICCV.2015.510 · DOI · Paper page
  43. 10.1145/3319535.3363269 · DOI · Paper page
  44. 10.1109/tcsvt.2021.3074259 · DOI · Paper page
  45. 10.1109/WIFS.2017.8267647 · DOI · Paper page
  46. 10.1145/3394171.3414034 · DOI · Paper page
  47. 10.1007/978-3-030-67832-6_12 · DOI
  48. 10.1109/CVPR.2018.00432 · DOI · Paper page

Cited by

See all 72

Metadata

Authors
Lu, W., Liu, L., Zhang, B., Luo, J., Zhao, X., Zhou, Y., & Huang, J.
Venue
IEEE Transactions on Neural Networks and Learning Systems
Published
2024-07
Volume
35
Issue
7
Pages
9366-9379
ISSN
  • 2162-237X (ISSN-L)
  • 2162-2388
OpenAlex
W4313639609
Cited by
72
References
32
FWCI
6.27
Type
journal article
Language
en
Open access
green
Funders
National Natural Science Foundation of China (U2001202, 62072480, U19B2022, U1636202)

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.