CoChat

MSTA-Net: Forgery Detection by Generating Manipulation Trace Based on Multi-Scale Self-Texture Attention

Yang, Jiachen, Xiao, Shuai, Li, Aiyun, Lu, Wen, Gao, Xinbo, Li, Yang · 2022 · IEEE Transactions on Circuits and Systems for Video Technology
Cited by 115

The DOI matches its Crossref record; 23 of the 23 references it cites were found in a registry or an index.

Abstract

Lots of Deepfake videos are circulating on the Internet, which not only damages the personal rights of the forged individual, but also pollutes the web environment. What’s worse, it may trigger public opinion and endanger national security. Therefore, it is urgent to fight deep forgery. Most of the current forgery detection algorithms are based on convolutional neural networks to learn the feature differences between forged and real frames from big data. In this paper, from the perspective of image generation, we simulate the forgery process based on image generation and explore possible trace of forgery. We propose a multi-scale self-texture attention Generative Network(MSTA-Net) to track the potential texture trace in image generation process and eliminate the interference of deep forgery post-processing. Firstly, a generator with encoder-decoder is to disassemble images and performed trace generation, then we merge the generated trace image and the original map, which is input into the classifier with Resnet as the backbone. Secondly, the self-texture attention mechanism(STA) is proposed as the skip connection between the encoder and the decoder, which significantly enhances the texture characteristics in the image disassembly process and assists the generation of texture trace. Finally, we propose a loss function called Prob-tuple loss restricted by classification probability to amend the generation of forgery trace directly. To verify the performance of the MSTA-Net, we design different experiments to verify the feasibility and advancement of the method. Experimental results show that the proposed method performs well on deep forged databases represented by FaceForensics++, Celeb-DF, Deeperforensics and DFDC, and some results are reaching the state-of-the-art.

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/tcsvt.2021.3133859

Cites

23 of 23 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

Show all 23 references

Research works printed but not linked: 31

  1. 10.1109/TCSVT.2021.3089724 · DOI
  2. 10.1109/TCSVT.2019.2945057 · DOI
  3. 10.1109/TCSVT.2019.2918852 · DOI
  4. Zhao, 2021, A transferable anti-forensic attack on forensic CNNs using a generative adversarial network, arXiv:2101.09568 · arXiv
  5. 10.1109/TCSVT.2019.2892608 · DOI
  6. Goodfellow, Generative adversarial nets, 2672
  7. Feng, 2020, Learning generalized spoof cues for face anti-spoofing, arXiv:2005.03922 · arXiv
  8. 10.1109/TCSVT.2021.3061153 · DOI
  9. 10.1109/TCSVT.2020.3014889 · DOI
  10. Dolhansky, 2020, The DeepFake detection challenge dataset, CoRR, abs/2006.07397 · arXiv
  11. 2018, Faceswap-GAN
  12. 2018, Faceswap: Deepfakes Software for All
  13. Li, 2019, FaceShifter: Towards high fidelity and occlusion aware face swapping, arXiv:1912.13457 · arXiv
  14. 10.1109/TCSVT.2021.3068294 · DOI
  15. 10.1145/3306346.3323035 · DOI · Paper page
  16. Karras, 2021, Alias-free generative adversarial networks, arXiv:2106.12423 · arXiv
  17. 10.1109/CVPR46437.2021.00991 · DOI · Paper page
  18. 10.1109/ICCV48922.2021.00209 · DOI · Paper page
  19. Agarwal, Protecting world leaders against deep fakes, 1
  20. 10.1109/WACV.2016.7477553 · DOI · Paper page
  21. Güera, We need no pixels: Video manipulation detection using stream descriptors, 1
  22. 10.1145/3297280.3297410 · DOI · Paper page
  23. 10.1109/CVPR.2018.00116 · DOI · Paper page
  24. 10.1109/ICCV.2019.00765 · DOI · Paper page
  25. 10.1109/TCSVT.2021.3074259 · DOI · Paper page
  26. 10.1109/TPAMI.2019.2928540 · DOI · Paper page
  27. Vaswani, 2017, Attention is all you need, CoRR, abs/1706.03762 · arXiv
  28. 10.1109/TCSVT.2018.2884203 · DOI
  29. 10.1016/j.future.2021.06.043 · DOI · Paper page
  30. 10.1109/WIFS49906.2020.9360901 · DOI · Paper page
  31. 10.1007/s10479-011-0841-3 · DOI · Paper page

Cited by

See all 115

Metadata

Authors
Yang, J., Xiao, S., Li, A., Lu, W., Gao, X., & Li, Y.
Venue
IEEE Transactions on Circuits and Systems for Video Technology
Published
2022-07
Volume
32
Issue
7
Pages
4854-4866
ISSN
  • 1051-8215 (ISSN-L)
  • 1558-2205
OpenAlex
W4205974231
Cited by
115
References
23
FWCI
7.67
Type
journal article
Language
en
Open access
closed
Funders
National Natural Science Foundation of China (61871283)

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: MSTA-Net: Forgery Detection by Generating Manipulation Trace Based on Multi-Scale Self-Texture Attention. https://app.cochat.ai/papers/10.1109/tcsvt.2021.3133859
The paper
Yang, J., Xiao, S., Li, A., Lu, W., Gao, X., & Li, Y. (2022). MSTA-Net: Forgery Detection by Generating Manipulation Trace Based on Multi-Scale Self-Texture Attention. IEEE Transactions on Circuits and Systems for Video Technology. https://doi.org/10.1109/tcsvt.2021.3133859

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.