CoChat

Deepfake Forensics via an Adversarial Game

Open access
Wang, Zhi, Guo, Yiwen, Zuo, Wangmeng · 2022 · IEEE Transactions on Image Processing
Cited by 49

The DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.

Abstract

With the progress in AI-based facial forgery (i.e., deepfake), people are concerned about its abuse. Albeit effort has been made for training models to recognize such forgeries, existing models suffer from poor generalization to unseen forgery technologies and high sensitivity to changes in image/video quality. In this paper, we advocate robust training for improving the generalization ability. We believe training with samples that are adversarially crafted to attack the classification models improves the generalization ability considerably. Considering that AI-based face manipulation often leads to high-frequency artifacts that can be easily spotted (by models) yet difficult to generalize, we further propose a new adversarial training method that attempts to blur out these artifacts, by introducing pixel-wise Gaussian blurring. Plenty of empirical evidence show that, with adversarial training, models are forced to learn more discriminative and generalizable features. Our code: https://github.com/ah651/deepfake_adv.

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/tip.2022.3172845

Cites

24 of 24 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 24 references

Research works printed but not linked: 37

  1. 2019, FaceSwap
  2. 10.1109/ICIP.2014.7026073 · DOI · Paper page
  3. 10.1109/ICCV.2019.00765 · DOI · Paper page
  4. Goodfellow, 2014, Explaining and harnessing adversarial examples
  5. Xiao, 2018, Spatially transformed adversarial examples
  6. 10.1145/1399504.1360638 · DOI
  7. 10.1145/2024156.2024164 · DOI · Paper page
  8. 10.1109/CVPR.2014.537 · DOI · Paper page
  9. 10.1145/3306346.3323035 · DOI · Paper page
  10. 2019, DeepFakes
  11. 2019, ZAO
  12. 10.3156/jsoft.29.5_177_2 · DOI · Paper page
  13. 10.1109/CVPR.2019.00379 · DOI · Paper page
  14. 10.1109/ICCV.2019.00728 · DOI · Paper page
  15. 10.1109/CVPR.2018.00702 · DOI · Paper page
  16. 10.1109/ICCV.2017.580 · DOI · Paper page
  17. 10.1117/12.2078399 · DOI · Paper page
  18. 10.1109/TIFS.2012.2202227 · DOI · Paper page
  19. 10.1109/WIFS.2017.8267647 · DOI · Paper page
  20. 10.1109/AVSS.2018.8639163 · DOI · Paper page
  21. 10.1109/CVPR46437.2021.00222 · DOI · Paper page
  22. 10.1109/CVPR46437.2021.00361 · DOI · Paper page
  23. Uesato, 2019, Are labels required for improving adversarial robustness?
  24. 10.1007/978-3-030-66823-5_14 · DOI
  25. 10.1109/ICCV.2019.00033 · DOI · Paper page
  26. 10.1007/978-3-030-58580-8_4 · DOI · Paper page
  27. 10.1109/ICCV.2017.244 · DOI · Paper page
  28. Farnia, Do GANs always have Nash equilibria?, 3029
  29. Mescheder, 2017, The numerics of GANs
  30. Tan, 2019, EfficientNet: Rethinking model scaling for convolutional neural networks
  31. Dufour, 2019, Contributing data to deepfake detection research, Google AI Blog, 1, 1
  32. Liu, 2019, On the variance of the adaptive learning rate and beyond
  33. Paszke, PyTorch: An imperative style, high-performance deep learning library, 32, 8026
  34. 10.1109/CVPR.2017.195 · DOI · Paper page
  35. 10.1109/TPAMI.2018.2868668 · DOI · Paper page
  36. 10.1109/CVPR.2016.308 · DOI · Paper page
  37. 10.1609/aaai.v31i1.11231 · DOI · Paper page

Cited by

See all 49

Metadata

Authors
Wang, Z., Guo, Y., & Zuo, W.
Venue
IEEE Transactions on Image Processing
Published
2022
Volume
31
Pages
3541-3552
ISSN
  • 1057-7149 (ISSN-L)
  • 1941-0042
OpenAlex
W3139371685
Cited by
49
References
24
FWCI
2.99
Type
journal article
Language
en
Open access
green
Funders
  • National Key Research and Development Program of China (2021ZD0112100)
  • National Natural Science Foundation of China (U19A2073)

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: Deepfake Forensics via an Adversarial Game. https://app.cochat.ai/papers/10.1109/tip.2022.3172845
The paper
Wang, Z., Guo, Y., & Zuo, W. (2022). Deepfake Forensics via an Adversarial Game. IEEE Transactions on Image Processing. https://doi.org/10.1109/tip.2022.3172845

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.