Skip to content
2000
  1. Home
  2. A-Z Publications
  3. Current Chinese Computer Science
  4. Volume 2, Issue 1
  5. Article
Volume 2, Issue 1
  • ISSN: 2665-9972
  • E-ISSN: 2665-9964

Abstract

With the development of face forgery techniques, the spread and malicious abuse of forged images have become a thought-provoking problem, and the face forgery detection technique has also attracted people's attention. Academia has carried out in-depth research and discussion on detection techniques. This review discussed different face forgery methods and detection techniques. Four categories of detection methods are introduced: 1) detection method based on spatial domain, 2) detection method based on the frequency domain, 3) detection method based on biological information, and 4) detection method of multiple feature domains. This paper discussed each detection method's evolution and development in recent years. We paid special attention to the detection method of multiple feature domains and focused on the progress that has been made and the challenges it faced. In addition, this paper discussed open issues and future development trends that should be paid attention to in this field.

© 2022 Bentham Science Publishers
Loading

Article metrics loading...

/content/journals/cccs/10.2174/2665997202666220818122419
2022-04-01
2025-06-27

  • From This Site

    /content/journals/cccs/10.2174/2665997202666220818122419
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. KingmaD.P. WellingM. Auto-encoding variational bayesarXiv preprint arXiv: 1312.61142013
     [Google Scholar]
  2. ChivukulaA.S. LiuW. Adversarial deep learning models with multiple adversaries.IEEE Trans. Knowl. Data Eng.20183161066107910.1109/TKDE.2018.2851247
     [Google Scholar]
  3. ChivukulaA. YangX. LiuW. ZhuT. ZhouW. Game the- oretical adversarial deep learning with variational adversaries.IEEE Trans. Knowl. Data Eng.2021331135683581
     [Google Scholar]
  4. GoodfellowI. Pouget-AbadieJ. MirzaM. XuB. Warde-FarleyD. OzairS. CourvilleA. BengioY. Generative adversarial nets.Adv. Neural Inf. Process. Syst.201426722680
     [Google Scholar]
  5. AnsariM.D. RashidE. SkandhaS.S. GuptaS.K. A comprehensive analysis of image forensics techniques: Challenges and future direction.Rec. Pat. Eng.2020458467
     [Google Scholar]
  6. MaternF. RiessC. StammingerM. “Exploiting visual artifacts to expose deepfakes and face manipulations”, 2019 IEEE Winter Applications of Computer Vision Workshops (WACVW), 07-11 January 2019.Waikoloa, HI, USA, IEEE2019839210.1109/WACVW.2019.00020
     [Google Scholar]
  7. LiL. BaoJ. ZhangT. YangH. ChenD. WenF. GuoB. Face x-ray for more general face forgery detectionProceedings of the IEEE/CVF conference on computer vision and patternrecognition, 13-19 June 2020, Seattle, WA, USA20205001501010.1109/CVPR42600.2020.00505
     [Google Scholar]
  8. AfcharD. NozickV. YamagishiJ. EchizenI. Mesonet: A compact facial video forgery detection networkIEEE international workshop on information forensics and security (WIFS), 11-13 December 2018, Hong Kong, China201917
     [Google Scholar]
  9. XuK. QinM. SunF. WangY. ChenY-K. RenF. Learning in the frequency domainProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition June, 2020Seattle, WA174017492020
     [Google Scholar]
  10. ZhangX. KaramanS. ChangS-F. Detecting and simulating artifacts in GAN fake images2019 IEEE International Workshop on Information Forensics and Security (WIFS) 09-12 December 2019Delft, Netherlands, IEEE16201910.1109/WIFS47025.2019.9035107
     [Google Scholar]
  11. DurallR. KeuperM. KeuperJ. Watch your up-convolution: Cnn based generative deep neural networks are failing to reproduce spectral distributionsProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 13-19 June 2020Seattle, WA, USA20207890789910.1109/CVPR42600.2020.00791
     [Google Scholar]
  12. FrankJ. EisenhoferT. SchönherrL. FischerA. KolossaD. HolzT. Leveraging frequency analysis for deep fake image recognitionProceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020Virtual Event202032473258
     [Google Scholar]
  13. LiY. ChangM-C. LyuS In ictu oculi: Exposing ai generated fake face videos by detecting eye blinkingarXiv preprint arXiv:1806.028772018
     [Google Scholar]
  14. CiftciU-A. DemirI. YinL. FakeCatcher: Detection of synthetic portrait videos using biological signalsEEE Trans. Pattern Anal. Mach. Intell.202010.1109/TPAMI.2020.300928732750816
     [Google Scholar]
  15. QiH. GuoQ. Juefei-XuF. XieX. MaL. FengW. LiuY. ZhaoJ. Deeprhythm: Exposing deepfakes with attentional visual heartbeat rhythmsProceedings of the 28th ACM International Conference on Multimedia431843272020
     [Google Scholar]
  16. Hernandez-OrtegaJ. TolosanaR. FierrezJ. MoralesA Deepfakeson-phys: Deepfakes detection based on heart rate estimationarXiv preprint arXiv:2010.004002020
     [Google Scholar]
  17. HuJ. LiaoX. WangW. QinZ. Detecting compressed deepfake videos in social networks using frame-temporality two-stream convolutional network.IEEE Trans. Circ. Syst. Video Tech.20213231089110210.1109/TCSVT.2021.3074259
     [Google Scholar]
  18. ChenS. YaoT-P. ChenY. DingS-H. LiJ-L. JiR.G. Local relation learning for face forgery detectionThe Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21)108110882021
     [Google Scholar]
  19. LiuH. LiX-D. ZhouW-B. ChenY-F. HeY. XueH. ZhangW-M. YuN-H. Spatial-phase shallow learning: Rethinking face forgery detection in frequency domain. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 20-25 June 2021Nashville, TN, USA772781202110.1109/CVPR46437.2021.00083
     [Google Scholar]
  20. KarrasT. LaineS. AilaT. A style-based generator architecture for generative adversarial networksProc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, 15-20 June 2019Long Beach, CA, USA, IEEE44014410201910.1109/CVPR.2019.00453
     [Google Scholar]
  21. RadfordA. MetzL. ChintalaS. Unsupervised representation learning with deep convolutional generative adversarial networks9th Conference on Artificial Intelligence and Robotics and 2nd Asia-Pacific International Symposium, 10-10 December 2018Kish Island, Iran, IEEE2018
     [Google Scholar]
  22. MirzaM. OsinderoS. Conditional generative adversarial nets.Comput. Sci.201426722680
     [Google Scholar]
  23. ChenX. DuanY. HouthooftR. SchulmanJ. SutskeverI. AbbeelP. InfoGAN: Interpretable representation learning by information maximizing generative adversarial netsNIPS’16: Proceedings of the 30th International Conference on Neural Information Processing SystemsDecember201621802188
     [Google Scholar]
  24. ZhangH. StackGAN: Text to photo-realistic image synthesis with stacked generative adversarial networks. 2017 IEEE International Conference on Computer Vision (ICCV)Venice, Italy20175908591610.1109/ICCV.2017.629
     [Google Scholar]
  25. TahmidM. AlamS. AkramM.k. Comparative analysis of generative adversarial networks and their variants23rd International Conference on Computer and Information Technique (ICCIT)20201610.1109/ICCIT51783.2020.9392660
     [Google Scholar]
  26. ChoiY. ChoiM. KimM. HaJ. KimS. ChooJ. StarGAN: Unified genera- tive adversarial networks for multi-domain image-to-image translationProc. IEEE/CVF Conference on Computer Vision and Pattern Recognition87898797201810.1109/CVPR.2018.00916
     [Google Scholar]
  27. LiuM. DingY. XiaM. LiuX. DingE. ZuoW. WenS. STGAN: A unified se- lective transfer network for arbitrary image attribute editingProc. IEEE/CVF Conference on Computer Vision and Pattern Recognition36733682201910.1109/CVPR.2019.00379
     [Google Scholar]
  28. ThiesJ. ZollhoferM. StammingerM. TheobaltC. NießnerM. Face2face: Real– time face capture and reenactment of RGB videosProc. IEEE/CVF Conference on Computer Vision and Pattern Recognition23872395201610.1145/2929464.2929475
     [Google Scholar]
  29. ThiesJ. ZollhöferM. NießnerM. Deferred neural rendering: Image synthesis using neural textures.ACM Trans. Graph.2019386611210.1145/3306346.3323035
     [Google Scholar]
  30. KawaiY. SeoM. ChenY-W. Automatic generation of facial expression using generative adversarial netsIEEE 7th Global Conference on Consumer Electronics (GCCE)201827828010.1109/GCCE.2018.8574866
     [Google Scholar]
  31. PumarolaA. AgudoA. MartinezA-M. SanfeliuA. NoguerF-M. GANimation: One-shot anatomically consistent facial animation.Int. J. Comput. Vis.2020128369871310.1007/s11263‑019‑01210‑3
     [Google Scholar]
  32. LiH. LiB. TanS. HuangJ. Identification of deep network generated images using disparities in color components.Signal Processing202017410761610.1016/j.sigpro.2020.107616
     [Google Scholar]
  33. NatarajL. MohammedT.M. ManjunathB.S. ChandrasekaranS. FlennerA. BappyJ.H. Roy-ChowdhuryA.K. Detecting GAN generated fake images using co-occurrence matricesElectronic Imaging201920195532-1532-710.2352/ISSN.2470‑1173.2019.5.MWSF‑532
     [Google Scholar]
  34. WangG. ZhouJ. WuY Exposing deep-faked videos by anomalous co-motion pattern detectionarXiv preprint arXiv:2008.048482020
     [Google Scholar]
  35. AndreasR. CozzolinoD. VerdolivaL. RiessC. ThiesJ. MatthiasN. Faceforensics: A large-scale video dataset for forgery detection in human facesarXiv preprint arXiv2018
     [Google Scholar]
  36. RosslerA. CozzolinoD. VerdolivaL. RiessC. ThiesJ. NießnerM. Faceforensics++: Learning to detect manipulated facial imagesProceedings of the IEEE International Conference on Computer Vision1112019
     [Google Scholar]
  37. LiY. YangX. SunP. QiH. LyuS. Celeb-df: A large-scale challenging dataset for deep- fake forensicsProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition320732162020
     [Google Scholar]
  38. DolhanskyB. BittonJ. PflaumB. LuJ. HowesR. WangM. FerrerC.C The deepfake detection challenge datasetarXiv preprint arXiv: 2006.073972020
     [Google Scholar]
  39. YangJ. LiA. XiaoS. LuW. GaoX. MTD-Net: Learning to detect deepfakes images by multi-scale texture difference.IEEE Trans. Inf. Forensics Security2021164234424510.1109/TIFS.2021.3102487
     [Google Scholar]
  40. HeK. ZhangX. RenS. SunJ. Deep residual learning for image recognition2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)770778201610.1109/CVPR.2016.90
     [Google Scholar]
  41. LimaO.D. FranklinS. BasuS. KarwoskiB. GeorgeA. Deepfake detection using spatiotemporal convolutional networksarXiv preprint arXiv20202006.14749
     [Google Scholar]
  42. SabirE. ChengJ. JaiswalA. W. AbdAlmageed, I. Masi, and P. Natarajan, “Recurrent convolutional strategies for face manipulation detection in videosCVPR Workshop2019
     [Google Scholar]
  43. WangS-Y. WangO. ZhangR. OwensA. EfrosA.A. CNN-generated images are surprisingly easy to spot… for now. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Seattle, WA, USA86928701202010.1109/CVPR42600.2020.00872
     [Google Scholar]
  44. KarrasT. AilaT. LaineS. LehtinenJ. Progressive growing of gans for improved quality, stability, and variationNeural and Evolutionary Computing, ariv2017
     [Google Scholar]
  45. LiuJ. ZhuK. LuW. LuoX. ZhaoX. A Lightweight 3D convolutional neural network for deepfake detection.Int. J. Intell. Syst.202111510.1002/int.22499
     [Google Scholar]
  46. LiuZ. QiX. TorrP.H.S. Global texture enhancement for fake face detection in the wildProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition80608069202010.1109/CVPR42600.2020.00808
     [Google Scholar]
  47. HanB. HanX. ZhangH. LiJ. CaoX. Fighting fake news: Two stream network for deepfake detection via learnable SRM.IEEE Trans. Biometrics Behav. Identity Sci.202133320331
     [Google Scholar]
  48. DangH. LiuF. StehouwerJ. LiuX. JainA.K. On the detection of digital face manipulationProceedings of the IEEE/CVF Conference on Computer Vision and Pattern recognition57815790202010.1109/CVPR42600.2020.00582
     [Google Scholar]
  49. ZhaoH. ZhouW. ChenD. WeiT. ZhangW. YuN. Multi-attentional deepfake detectionProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition218521942021
     [Google Scholar]
  50. CholletF. Xception: Deep learning with depthwise separable convolutions2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)18001807201710.1109/CVPR.2017.195
     [Google Scholar]
  51. WuX. XieZ. GaoY.T. XiaoY. Sstnet: Detecting manipulated faces through spatial, steganalysis and temporal featuresICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)20202952295610.1109/ICASSP40776.2020.9053969
     [Google Scholar]
  52. ZhuX. WangH. FeiH. LeiZ. LiS-Z. Face forgery detection by 3D decompositionProc. IEEE/CVF Conference on Computer Vision and Pattern Recognition292929392020
     [Google Scholar]
  53. YangX. LiY. LyuS. Exposing deep fakes using inconsistent head posesICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)Brighton, UK20198261826510.1109/ICASSP.2019.8683164
     [Google Scholar]
  54. BappyJ.H. SimonsC. NatarajL. ManjunathB.S. Roy-ChowdhuryA.K. Hybrid LSTM and encoder-decoder architecture for detection of image forgeries.IEEE Trans. Image Process.20192873286330010.1109/TIP.2019.2895466 30703026
     [Google Scholar]
  55. MasiI. KillekarA. MascarenhasR.M. GurudattS.P. AbdAlmageedW. Two-branch recurrent network for isolating deepfakes in videosEuropean Conference on Computer Vision2020667684
     [Google Scholar]
  56. LiJ. XieH. LiJ. WangZ. ZhangY. Frequency-aware discriminative feature learning supervised by single-center loss for face forgery detectionProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 20-25 June 2021Nashville, TN, USA, IEEE64586467202110.1109/CVPR46437.2021.00639
     [Google Scholar]
  57. LuoY. ZhangY. YanJ. LiuW. Generalizing face forgery detection with high-frequency features. Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition, 20-25 June 2021Nashville, TN, USA, IEEE1631716326202110.1109/CVPR46437.2021.01605
     [Google Scholar]
/content/journals/cccs/10.2174/2665997202666220818122419
Loading
An Overview of Face Image Forgery Detection
Current Chinese Computer Science 2, e180822207638 (2022); https://doi.org/10.2174/2665997202666220818122419
/content/journals/cccs/10.2174/2665997202666220818122419
/content/journals/cccs/10.2174/2665997202666220818122419
Loading

Data & Media loading...


  • Article Type:     Review Article
Keyword(s): Deepfake detection; face manipulation; image processing; media forensics; multiple feature domains; neural network

Most Cited Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test