DEEPFAKE FORENSICS USING VISION TRANSFORMER MODELS VIDEO

The integration of Vision Transformers, meta-learning, and 3D decomposition techniques offers a powerful solution for modern deepfake forensics. ViTs provide global spatial modeling, while physical 3D decomposition reveals lighting and geometric inconsistencies. Meta-learning enables strong domain generalization, ensuring stable detection even against unseen manipulations. This unified framework represents a major step toward reliable and future-proof deepfake detection systems.

[1]   Bennett, C. H., & Brassard, G. (1984). Quantum cryptography: Public key distribution and coin tossing. Proceedings of IEEE International Conference on Computers, Systems and Signal Processing, Bangalore, India. [2]   Heo, Y., Kim, Y., Kim, H., & Kim, J. (2023). MEViT: Generalization of Deepfake Detection with Meta-Learning EfficientNet-Vision Transformer. IEEE Access. [3]   Li, L., Bao, J., Yang, H., Chen, D., & Wen, F. (2020). Face forgery detection by 3D decomposition and composition search. IEEE Transactions on Pattern Analysis and Machine Intelligence. [4]   Li, T., & Zhang, H. (2020). Deep learning applications in video security. Journal of Information Security and Applications. [5]   Yuan, X., Li, Z., & Lyu, S. (2019). 3D- based face analysis for deepfake detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. [6]   Afchar, D., Nozick, V., Yamagishi, J., & Echizen, I. (2018). MesoNet: A compact facial video forgery detection network. IEEE International Workshop on Information Forensics and Security. [7]   Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., & Nießner, M. (2019). FaceForensics++: Learning to detect manipulated facial images. IEEE International Conference on Computer Vision (ICCV). [8]    Li, Y., Chang, M., & Lyu, S. (2018). In Ictu Oculi: Exposing AI generated fake face videos by detecting eye blinking. IEEE International Workshop on Information Forensics and Security. [9]    Nguyen, H. H., Yamagishi, J., & Echizen, I. (2019). Capsule-Forensics: Using capsule networks to detect forged images and videos. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). [10]    Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. IEEE Conference on Computer Vision and Pattern Recognition (CVPR).