CoChat

Unsupervised Learning-Based Framework for Deepfake Video Detection

Zhang, Li, Qiao, Tong, Xu, Ming, Zheng, Ning, Xie, Shichuang · 2023 · IEEE Transactions on Multimedia
Cited by 64

The DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.

Abstract

With the continuous development of computer hardware equipment and deep learning technology, it is easier for people to swap faces in videos by currently-emerging multimedia tampering tools, such as the most popular deepfake. It would bring a series of new threats of security. Although many forensic researches have focused on this new type of manipulation and achieved high detection accuracy, most of which are based on supervised learning mechanism with requiring a large number of labeled samples for training. In this paper, we first develop a novel unsupervised detection manner for identifying deepfake videos. The main fundamental behind our proposed method is that the face region in the real video is taken by the camera while its counterpart in the deepfake video is usually generated by the computer; the provenance of two videos is totally different. Specifically, our method includes two clustering stages based on Photo-Response Non-Uniformity (PRNU) and noiseprint feature. Firstly, the PRNU fingerprint of each video frame is extracted, which is used to cluster the full-size identical source video (regardless of its real or fake). Secondly, we extract the noiseprint from the face region of the video, which is used to identify (re-cluster for the task of binary classification) the deepfake sample in each cluster. Numerical experiments verify our proposed unsupervised method performs very well on our own dataset and the benchmark FF++ dataset. More importantly, its performance rivals that of the supervised-based state-of-the-art detectors.

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/tmm.2022.3182509

Cites

25 of 25 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 25 references

Research works printed but not linked: 34

  1. 10.1109/CVPR46437.2021.00361 · DOI · Paper page
  2. 10.1109/TIFS.2019.2918644 · DOI
  3. tan, 0, Efficientnet: Rethinking model scaling for convolutional neural networks, Int Conf Mach Learn, 6105
  4. agarwal, 0, Protecting world leaders against deep fakes, Proc CVPR Workshops, 38
  5. 10.1109/ICCVW.2019.00213 · DOI · Paper page
  6. 10.1109/ACCESS.2021.3070478 · DOI
  7. shi, 2000, Normalized cuts and image segmentation, IEEE Trans Pattern Anal Mach Intell, 22, 888, 10.1109/34.868688 · DOI · Paper page
  8. 10.1109/TIFS.2020.2985544 · DOI
  9. dufour, 2019, Contributing data to deepfake detection research, Google AI Blog, 1, 1
  10. koopman, 0, Detection of deepfake video manipulation, Proc 20th Ir Mach Vis Image Process Conf, 133
  11. verdoliva, 0, Extracting camera-based fingerprints for video forensics, Proc IEEE Conf Comp Vis Pattern Recognit, 130
  12. 10.1117/12.640109 · DOI · Paper page
  13. 10.1007/978-3-319-46448-0_30 · DOI · Paper page
  14. 10.1016/j.image.2017.04.009 · doi:10.1016/j.image.2017.04.009
  15. 10.1155/2021/6652727 · DOI
  16. 10.1007/s00530-017-0538-9 · DOI
  17. 10.1109/TMM.2019.2959443 · DOI
  18. 10.3390/s20226668 · DOI
  19. 10.1007/s11042-018-6809-4 · DOI
  20. 10.1109/TMM.2020.3013449 · DOI
  21. 10.1109/TIFS.2017.2692683 · DOI · Paper page
  22. 10.1016/j.image.2014.07.003 · DOI
  23. 10.1186/s13635-020-0101-7 · DOI
  24. 10.1109/CVPR46437.2021.00573 · DOI · Paper page
  25. 10.1109/TMM.2021.3050057 · DOI
  26. 10.1007/978-3-642-04431-1_19 · doi:10.1007/978-3-642-04431-1_19
  27. 10.1109/TMM.2018.2872863 · DOI · Paper page
  28. 10.1109/TMM.2015.2455417 · DOI
  29. 10.1109/CVPR.2018.00116 · DOI · Paper page
  30. 10.1109/AVSS.2018.8639163 · DOI · Paper page
  31. 10.1109/TCSVT.2021.3074259 · DOI · Paper page
  32. 10.1117/12.907495 · DOI · Paper page
  33. 10.1109/IJCNN52387.2021.9534089 · DOI · Paper page
  34. mittal, 0, Emotions don’t lie: An audio-visual deepfake detection method using affective cues, Proc 28th ACM Int Conf Multimedia, 2823

Cited by

See all 64

Metadata

Authors
Zhang, L., Qiao, T., Xu, M., Zheng, N., & Xie, S.
Venue
IEEE Transactions on Multimedia
Published
2023
Volume
25
Pages
4785-4799
ISSN
  • 1520-9210 (ISSN-L)
  • 1941-0077
OpenAlex
W4285226122
Cited by
64
References
25
FWCI
4.13
Type
journal article
Language
en
Open access
closed
Funders
  • Fundamental Research Funds for the Provincial Universities of Zhejiang (GK219909299001-007)
  • Open Projects Program of National Laboratory of Pattern Recognition

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: Unsupervised Learning-Based Framework for Deepfake Video Detection. https://app.cochat.ai/papers/10.1109/tmm.2022.3182509
The paper
Zhang, L., Qiao, T., Xu, M., Zheng, N., & Xie, S. (2023). Unsupervised Learning-Based Framework for Deepfake Video Detection. IEEE Transactions on Multimedia. https://doi.org/10.1109/tmm.2022.3182509

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.