Deepfake face Detection using Deep Learning Technique: A Symmetric Review
Main Article Content
Abstract
The rapid advancement of artificial intelligence and deep learning has enabled the creation of highly realistic synthetic facial content, commonly known as deepfakes. Although deepfake technology has beneficial applications in entertainment, education, and digital media, its misuse poses serious challenges related to misinformation, identity theft, privacy, and digital security. Deepfake face detection has therefore emerged as an important research area in computer vision and multimedia forensics. This symmetric review provides a comprehensive analysis of deep learning-based approaches developed for detecting manipulated facial images and videos. The review examines conventional Convolutional Neural Networks (CNNs), transfer-learning models, recurrent architectures, and advanced networks such as ResNet, DenseNet, EfficientNet, and Vision Transformer-based approaches. It systematically compares these techniques in terms of detection accuracy, robustness, computational complexity, dataset requirements, and generalization capability. Particular attention is given to facial preprocessing, frame extraction, feature representation, spatial and temporal artifact analysis, data augmentation, and evaluation metrics. The review also discusses widely used deepfake datasets and highlights challenges associated with compression, unseen manipulation techniques, cross-dataset performance, and adversarial attacks. Finally, emerging research directions, including multimodal learning, explainable artificial intelligence, lightweight detection models, and hybrid spatial-temporal architectures, are discussed. The study provides a structured perspective on the current state of deepfake face detection and identifies promising opportunities for developing more reliable, generalizable, and real-time detection systems.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
References
Ali Raza, Kashif Munir and Mubarak Almutairi, “A Novel Deep Learning Approach for Deepfake Image Detection”, Apply Science, pp. 01-15, 2022.
Zobaed, S.; Rabby, F.; Hossain, I.; Hossain, E.; Hasan, S.; Karim, A.; Hasib, K.M. Deepfakes: Detecting forged and synthetic media content using machine learning. In Artificial Intelligence in Cyber Security: Impact and Implications; Springer: Berlin/Heidelberg, Germany, 2021; pp. 177–201.
Thambawita, V.; Isaksen, J.L.; Hicks, S.A.; Ghouse, J.; Ahlberg, G.; Linneberg, A.; Grarup, N.; Ellervik, C.; Olesen, M.S.; Hansen, T.; et al. DeepFake electrocardiograms using generative adversarial networks are the beginning of the end for privacy issues in medicine. Sci. Rep. 2021, 11, 21869.
Ahmed, M.F.B.; Miah, M.S.U.; Bhowmik, A.; Sulaiman, J.B. Awareness to Deepfake: A resistance mechanism to Deepfake. In Proceedings of the 2021 International Congress of Advanced Technology and Engineering (ICOTEN), Taiz, Yemen, 4–5 July 2021; pp. 1–5.
Y. Nirkin, L. Wolf, Y. Keller, T. Hassner, Deepfake detection based on discrepancies between faces and their context, IEEE Transactions on Pattern Analysis and Machine Intelligence 44 (10) (2021) 6111–6121.
Brian Dolhansky, Russ Howes, Ben Pflaum, Nicole Baram, and Cristian Canton Ferrer. The Deepfake Detection Challenge (DFDC) Preview Dataset. arXiv eprints, page arXiv:1910.08854, 2019.
Brian Dolhansky, Joanna Bitton, Ben Pflaum, Jikuo Lu, Russ Howes, Menglin Wang, and Cristian Canton Ferrer. The DeepFake Detection Challenge Dataset. arXiv e-prints, page arXiv:2006.07397, 2020.
Md Shohel Rana, Mohammad Nur Nobi, Beddhu Murali, and Andrew H Sung. Deepfake detection: A systematic literature review. IEEE access, 10:25494–25513, 2022.
Jin, B.; Cruz, L.; Gonçalves, N. Deep facial diagnosis: Deep transfer learning from face recognition to facial diagnosis. IEEE Access 2020, 8, 123649–123661.
Lewis, J.K.; Toubal, I.E.; Chen, H.; Sandesera, V.; Lomnitz, M.; Hampel-Arias, Z.; Prasad, C.; Palaniappan, K. Deepfake Video Detection Based on Spatial, Spectral, and Temporal Inconsistencies Using Multimodal Deep Learning. In Proceedings of the 2020 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), Washington DC, DC, USA, 13–15 October 2020; pp. 1–9.
Lee, H.; Park, S.H.; Yoo, J.H.; Jung, S.H.; Huh, J.H. Face recognition at a distance for a stand-alone access control system. Sensors 2020, 20, 785.
Z. He, W. Zuo, M. Kan, S. Shan, and X. Chen. Attgan: Facial attribute editing by only changing what you want. IEEE Transactions on Image Processing, 28(11): 5464–5478, 2019.
Nguyen, T. T., Nguyen, C. M., Nguyen, D. T., Nguyen, D. T., & Nahavandi, S. Deep learning for deepfakes creation and detection, 2019, arXiv preprint arXiv:1909.11573.
Sergey Tulyakov, Ming-Yu Liu, Xiaodong Yang, and Jan Kautz. Mocogan: Decomposing motion and content for video generation. pages 1526–1535, 2018.
Guha Balakrishnan, Amy Zhao, Adrian V. Dalca, Fr´edo Durand, and John Guttag. Synthesizing images of humans in unseen poses. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
Anuj Badale et al., "Deep fake detection using neural networks", 15th IEEE international conference on advanced video and signal-based surveillance (AVSS), 2018.
Soumya Tripathy, Juho Kannala, and Esa Rahtu. Icface: Interpretable and controllable face reenactment using gans. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2020.
Wayne Wu, Yunxuan Zhang, Cheng Li, Chen Qian, and Chen Change Loy. Reenactgan: Learning to reenact faces via boundary transfer. In Proceedings of the European Conference on Computer Vision (ECCV), 2018.