CoChat
Sign Up
Cited by 23Digital Media Forensic DetectionGenerative Adversarial Networks and Image SynthesisMisinformation and Its Impacts

The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.

Deepfakes Detection Methods: A Literature Survey

Weerawardana, MC, Fernando, TGI·2021·2021 10th International Conference on Information and Automation for Sustainability (ICIAfS)
DOI 10.1109/iciafs52090.2021.9606067
Open this paper in CoChat — free account

Abstract

Recently, a great amount of concern has been attracted to the phenomena of DeepFake, which has been created for capturing and reenacting faces in a video and swap a face with someone else’s face using neural networks. In Deepfake technology, a computer-generated fake video shows fictional contents as real things. Many unbelievable applications in this technology are starting to be explored. Currently, malicious usages of fake videos are gaining in the computerized world like fake news, celebrity pornographic videos, revenge porn, and financial frauds. So, celebrities, politicians and famous people are facing mostly to Deepfake detection problem. Human’s naked eyes are weak to directly identify the difference between real videos and Deepfake videos because they are quite realistic. So, bothered people require an automated computerized Deepfake detection tool. This paper reviews existing Deepfake detection methods using traditional methods and deep learning technologies. Further this paper discussing the limitations of current methods and availability of datasets in the society. According to the literature, there is not a highly accurate and automated detection method to identify Deepfakes. The unavailability of efficient Deepfake detection method is a big challenge to the world due to the ease of generating Deepfake videos and their rapid spread. However, there are many efforts to solve this phenomenon and deep learning related methods show remarkable performance than other me…

Overview

Integrity signals

Registry

Crossref · 10.1109/iciafs52090.2021.9606067

Cites

6 of 6 references verified0 citation errors · 0 not checkable

Statistics

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

Verification

Claims the paper makes

This paper’s full text isn’t openly available, 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

Cites

Research works printed but not linked: 42

  1. szegedy, 2016, Rethinking the inception architecture for computer vision, In CVPR, 2818
  2. 10.1109/WIFS.2018.8630761 · DOI · Paper page
  3. 10.1109/CVPR.2016.261 · DOI
  4. 10.1109/TCSVT.2016.2645723 · DOI
  5. sabir, 0, Recurrent Convolutional Strategies for Face Manipulation Detection in Videos, USC Information Sciences Institute
  6. chollet, 2017, XceptionNet: Deep Learning with Depthwise Separable Convolutions, In CVPR, 1251
  7. guera, 2018, Deepfake video detection using recurrent neural networks, 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), 1
  8. 10.1109/ICASSP.2019.8683164 · DOI · Paper page
  9. cozzolino, 2018, Forensictransfer: Weakly-supervised domain adaptation for forgery detection, arXiv preprint arXiv 1812 02588
  10. 10.5244/C.31.8 · DOI
  11. 10.1007/978-1-4614-0757-7 · DOI
  12. 10.1109/CVPR.2017.75 · DOI
  13. 10.7551/mitpress/10451.001.0001 · DOI
  14. 10.1109/ICCCT.2014.7001509 · DOI
  15. 10.1007/978-3-030-01231-1_11 · DOI
  16. wu, 2018, Image copymove forgery detection via an end-to-end deep neural network, WACV, 1907
  17. 10.1109/CVPR.2019.00977 · DOI
  18. 10.1109/ACCESS.2018.2819624 · DOI
  19. 10.1109/CVPRW.2017.229 · DOI · Paper page
  20. mccloskey, 2018, Detecting gan generated imagery using color cues, arXiv preprint arXiv 1812 08942
  21. rossler, 2018, Face Forensics: A Large-scale Video Dataset for Forgery Detection in Human Faces, arXiv 1803 09179[cs]
  22. li, 2018, Detection of deep network generated images using disparities in color components, arXiv preprint arXiv 1808 07536
  23. 0, Fakeapp
  24. 10.1145/2929464.2929475 · DOI
  25. 10.1109/BTAS.2017.8272754 · DOI · Paper page
  26. 10.1109/ICCV.2019.00009 · DOI · Paper page
  27. 10.1109/CVPRW.2017.230 · DOI
  28. 2019, MarekKowalski/FaceSwap development by creating an account on GitHub
  29. 0, FaceApp
  30. 10.1109/WACV.2018.00111 · DOI
  31. 2018, Deepfake project - nonofficial project based on original deepfakes thread
  32. jeon, 2020, FakeTalkerDetect: Effective and practical realistic neural talking head detection with a highly unbalanced dataset, ICCV Workshop
  33. 10.1016/j.jvcir.2017.09.003 · DOI
  34. 10.1109/WACVW.2019.00020 · DOI · Paper page
  35. nguyen, 2019, Multitask learning for detecting and segmenting manipulated facial images and videos, preprint arXiv 1906 06876
  36. 10.1145/2909827.2930786 · DOI · Paper page
  37. li, 2018, Exposing deepfake videos by detecting face warping artifacts, preprint arXiv 1811 00656
  38. 10.1109/ICCV.2017.397 · DOI · Paper page
  39. 10.1109/LSP.2016.2603342 · DOI · Paper page
  40. 10.1109/WIFS.2017.8267647 · DOI
  41. 10.1145/3306346.3323035 · DOI
  42. 10.1145/3072959.3073640 · DOI · Paper page

Cited by

Sorted by citations

See all 23

Metadata

Authors
Weerawardana, M., & Fernando, T.
Affiliations
University of Sri Jayewardenepura (LK)
Venue
2021 10th International Conference on Information and Automation for Sustainability (ICIAfS)
Publisher
IEEE
Published
2021-08-11
Pages
76-81
DOI
10.1109/iciafs52090.2021.9606067
OpenAlex
W3212277844
Cited by
23
References
6
Citations by year
2026: 1 · 2025: 5 · 2024: 8 · 2023: 6 · 2022: 3
FWCI
1.39
Type
conference paper
Language
en
Open access
closed
Licence
Locations
International Conference on Information and Automation for Sustainability (ICIAfS) (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
  • Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
Keywords
deepfake detection, face swapping, synthetic video detection, deep learning, deepfake datasets, fake news, financial fraud

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