Deepfake Video Detection: A Comprehensive Review

Abstract: Deepfake technology, driven by Generative Adversarial Networks (GANs) and diffusion models, presents significant political, social, and economic threats. This review consolidates insights from over 30 scholarly contributions on deepfake detection techniques, datasets, evaluation metrics, and ongoing challenges. We examine both traditional methods and modern deep learning strategies, including convolutional neural networks (CNNs), transformers, multimodal architectures, and ensemble frameworks. Key benchmark datasets—DFDC, FaceForensics++, and Deepfake-Eval-2024—are comparatively analyzed. Performance metrics such as accuracy, AUC, F1-score, and Matthew’s correlation coefficient (MCC), along with adversarial robustness, are critically assessed. Identified limitations include poor cross-domain generalization, suboptimal real-time performance, and dataset bias. The review proposes future directions including adaptive detection models, enhanced multimodal fusion, model interpretability, and the need for unified global standards in forensic validation.

Deepfake, Video Forensics, Detection, CNN, GAN, Diffusion Models, Benchmark Datasets, Adversarial Robustness, Multimodal Fusion

1. Greenberg, J., White, H. C., Carrier, S., & Scherle, R. (2009). A metadata best practice for a scientific data repository. Journal of Library Metadata, 9(3-4), 194-212. [Google Scholar] [Crossref]

2. Mathis, R. M., & Caughey, L. (2005, January). A metadata model for electronic images. In Proceedings of the 38th Annual Hawaii International Conference on System Sciences (pp. 112a-112a). IEEE. [Google Scholar] [Crossref]

3. Mani, R. G., Parthasarathy, R., Eswaran, S., & Honnavalli, P. (2022). A survey on digital image forensics: Metadata and image forgeries. In Workshop on Applied Computing, January 27-28, 22 (Vol. 55, pp. 22-55). [Google Scholar] [Crossref]

4. Chen, P. L., Cheng, Y. C., & Chen, K. (2018). Analysis of social media data: an introduction to the characteristics and chronological process. Big Data in Computational Social Science and Humanities, 297-321. [Google Scholar] [Crossref]

5. Spyrou, E., & Mylonas, P. (2016). Analyzing Flickr metadata to extract location-based information and semantically organize its photo content. Neurocomputing, 172, 114-133. [Google Scholar] [Crossref]

6. Varthis, E., Poulos, M., Giarenis, I., & Papavlasopoulos, S. (2020). Automatic metadata extraction via image processing using Migne’s Patrologia Graeca. International Journal of Metadata, Semantics and Ontologies, 14(4), 265-278. [Google Scholar] [Crossref]

7. Le Bourgeois, F., & Kaileh, H. (2004). Automatic metadata retrieval from ancient manuscripts. In Document Analysis Systems VI: 6th International Workshop, DAS 2004, Florence, Italy, September 8-10, 2004. Proceedings 6 (pp. 75-89). Springer Berlin Heidelberg. [Google Scholar] [Crossref]

8. Bharati, A., Moreira, D., Brogan, J., Hale, P., Bowyer, K., Flynn, P., ... & Scheirer, W. (2019, January). Beyond pixels: Image provenance analysis leveraging metadata. In 2019 IEEE winter conference on applications of computer vision (WACV) (pp. 1692-1702). IEEE. [Google Scholar] [Crossref]

9. Ingale, S., & Mehta, M. (2013). Characterizing suspicious images in social media using exif metadata. International Journal of Advance Computational Engineering and Networking. [Google Scholar] [Crossref]

10. Sugiantoro, B., & Prayudi, Y. (2018). Corelation Analysis Of Forensic Metadata For Digital Evidence. International Journal of Computer Science & Information Security, 16(3), 85. [Google Scholar] [Crossref]

11. Liu, X., Wang, M., & Huet, B. (2016). Event analysis in social multimedia: a survey. Frontiers of Computer Science, 10, 433-446. [Google Scholar] [Crossref]

12. Mombelli, S., Lyle, J. R., & Breitinger, F. (2024). FAIRness in digital forensics datasets’ metadata–and how to improve it. Forensic Science International: Digital Investigation, 48, 301681. [Google Scholar] [Crossref]

13. Saranya, K., Paulraj, M., & Brindha, M. (2022, April). A survey on feature selection and classification techniques for EEG signal processing. In Proceedings of International Conference on Deep Learning, Computing and Intelligence: ICDCI 2021 (pp. 155-165). Singapore: Springer Nature Singapore. [Google Scholar] [Crossref]

14. McAuley, J., & Leskovec, J. (2012). Image labeling on a network: using social-network metadata for image classification. In Computer Vision–ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part IV 12 (pp. 828-841). Springer Berlin Heidelberg. [Google Scholar] [Crossref]

15. Riggs, C., Douglas, T., & Gagneja, K. (2018, October). Image mapping through metadata. In 2018 Third International Conference on Security of Smart Cities, Industrial Control System and Communications (SSIC) (pp. 1-8). IEEE. [Google Scholar] [Crossref]

16. Näslund, A. (2024). Image metadata. From information management to interpretative practice. Museum Management and Curatorship, 39(4), 398-418. [Google Scholar] [Crossref]

17. Kumar, P. R., Srikanth, C., & Sailaja, K. L. (2016). Location Identification of the Individual based on Image Metadata. Procedia Computer Science, 85, 451-454. [Google Scholar] [Crossref]

18. Smith, K. R., Saunders, S., & Kejser, U. B. (2014, June). Making the case for embedded metadata in digital images. In Archiving Conference (Vol. 11, pp. 52-57). Society for Imaging Science and Technology. [Google Scholar] [Crossref]

19. Tavakoli, M., Elias, M., Kismihók, G., & Auer, S. (2021, April). Metadata analysis of open educational resources. In LAK21: 11th International Learning Analytics and Knowledge Conference (pp. 626-631). [Google Scholar] [Crossref]

20. Hossain, M. A., & Haque, B. I. (2022, January). An Analytic Solution for the Helmholtz-Duffing Oscillator by Modified Mickens’ Extended Iteration Procedure. In International Conference on Mathematics and Computing (pp. 689-700). Singapore: Springer Nature Singapore. [Google Scholar] [Crossref]

21. Noufal, P. P. (2005). Metadata: Automatic generation and extraction. [Google Scholar] [Crossref]

22. Sarvas, R., Herrarte, E., Wilhelm, A., & Davis, M. (2004, June). Metadata creation system for mobile images. In Proceedings of the 2nd international conference on Mobile systems, applications, and services (pp. 36-48). [Google Scholar] [Crossref]

23. Holland, R., Leingang, O., Bogunović, H., Riedl, S., Fritsche, L., Prevost, T., ... & Menten, M. J. (2024). Metadata-enhanced contrastive learning from retinal optical coherence tomography images. Medical Image Analysis, 103296. [Google Scholar] [Crossref]

24. Linkert, M., Rueden, C. T., Allan, C., Burel, J. M., Moore, W., Patterson, A., ... & Swedlow, J. R. (2010). Metadata matters: access to image data in the real world. Journal of Cell Biology, 189(5), 777-782. [Google Scholar] [Crossref]

25. Tesic, J. (2005). Metadata practices for consumer photos. IEEE MultiMedia, 12(3), 86-92. [Google Scholar] [Crossref]

26. Lim, S., & Li Liew, C. (2011, September). Metadata quality and interoperability of GLAM digital images. In Aslib Proceedings (Vol. 63, No. 5, pp. 484-498). Emerald Group Publishing Limited. [Google Scholar] [Crossref]

27. Chakraborty, C., Gupta, B., & Ghosh, S. K. (2014). Mobile metadata assisted community database of chronic wound images. Wound Medicine, 6, 34-42. [Google Scholar] [Crossref]

28. Haucke, M., Heinzel, S., & Liu, S. (2024). Social mobile sensing and problematic alcohol consumption: Insights from smartphone metadata. International Journal of Medical Informatics, 188, 105486. [Google Scholar] [Crossref]

29. Chen, Y., Sherren, K., Smit, M., & Lee, K. Y. (2023). Using social media images as data in social science research. New Media & Society, 25(4), 849-871. [Google Scholar] [Crossref]

30. McAuley, J., & Leskovec, J. (2012). Image labeling on a network: using social-network metadata for image classification. In Computer Vision–ECCV 2012: 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part IV 12 (pp. 828-841). Springer Berlin Heidelberg. [Google Scholar] [Crossref]

31. Schreck, T., & Keim, D. (2012). Visual analysis of social media data. Computer, 46(5), 68-75. [Google Scholar] [Crossref]

32. Ramesh Kumar P., Ch Srikanth, KL Sailaja. “Location Identification of the Individual based on Image Metadata.” Procedia Computer Science, vol. 85, 2016, pp. 451-454. [Google Scholar] [Crossref]

• Advanced Digital Communication Strategies: A Comprehensive Analysis
• Developing an Explainable AI System for Digital Forensics: Enhancing Trust and Transparency in Flagging Events for Legal Evidence
• The Global Impact of Government Censorship on Women’s Access to Information: A Literature Review
• "Reimagining Higher Education Workspaces: A Review on The Transformative Role of Digital Technology Adoption"
• Improved CSP Efficiency: Innovations and Challenges in Thermal Energy Storage Systems