Abstract

The rapid evolution of deep generative models has enabled the creation of highly realistic deepfake videos, posing significant threats to digital media authenticity, privacy and public trust. Modern deepfake generation techniques based on Generative Adversarial Networks (GANs) [1], autoencoders [2] and neural rendering models [3] can synthesize facial expressions, lip movements and identities with remarkable realism, making manual detection increasingly unreliable. This paper presents a comprehensive survey of deepfake video detection techniques with a focus on hybrid multimodal approaches that integrate spatial, temporal and physiological features [4, 5]. Existing methods based on visual artifacts, temporal inconsistencies, frequency-domain analysis and biological signal extraction such as remote photoplethysmography (rPPG) [5, 10] are systematically reviewed. The survey further examines hierarchical fusion architectures, benchmark datasets [2, 3], evaluation protocols and real-world deployment challenges. Key limitations and open research directions are identified to guide the development of robust, generalizable and real-time deepfake detection systems.

References

• Y. Li, X. Yang, P. Sun, H. Qi and S. Lyu, “Face x-ray for more general face forgery detection,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition (CVPR), 2020.
• A. Roessler, D. Cozzolino, L. Verdoliva, C. Riess, J. Thies and M. Niessner, “FaceForensics++: Learning to detect manipulated facial images,” in Proc. IEEE Int. Conf. Computer Vision (ICCV), 2019.
• B. Dolhansky et al., “The deepfake detection challenge dataset,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition Workshops, 2020.
• J. Hernandez-Ortega et al., “DeepFakesON-Phys: Deepfake detection based on heart rate estimation,” IEEE Transactions on Information Forensics and Security, 2021.
• T. Wang et al., “rPPG-based deepfake detection using physiological signals,” IEEE Access, 2022.
• C. Ciftci, I. Demir and L. Yin, “FakeCatcher: Detection of synthetic portrait videos using biological signals,” IEEE Transactions on Information Forensics and Security, 2020.
• P. Korshunov and S. Marcel, “Deepfakes: A new threat to face recognition? Assessment and detection,” in Proc. IEEE Int. Conf. Biometrics: Theory, Applications and Systems (BTAS), 2018.
• D. Guera and E. J. Delp, “Deepfake video detection using recurrent neural networks,” in Proc. IEEE Int. Conf. Advanced Video and Signal Based Surveillance (AVSS), 2018.
• Z. Zhao et al., “Multi-attentional deepfake detection,” in Proc. IEEE Int. Conf. Computer Vision (ICCV), 2021.
• S. Mittal et al., “Emotions don’t lie: An audio-visual deepfake detection method,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition Workshops, 2020.
• K. Shiohara and T. Yamasaki, “Detecting deepfakes with selfblended images,” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 1876–1885.
• J. Frank, T. Eisenhofer, L. Schonherr, A. Fischer, D. Kolossa and T. Holz, “Leveraging frequency analysis for deepfake image recognition,” in Proc. International Conference on Machine Learning (ICML), 2020, pp. 3247–3258.
• H. H. Nguyen, F. Fang, J. Yamagishi and I. Echizen, “Capsule-forensics: Using capsule networks to detect forged images and videos,” in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, pp. 2307–2311.
• L. Verdoliva, “Media forensics and deepfakes: An overview,” IEEE Journal of Selected Topics in Signal Processing,part vol. 14, no. 5, pp. 910–932, 2020.
• Y. Li and S. Lyu, “Exposing deepfake videos by detecting face warping artifacts,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2019, pp. 46–52.
• Z. Wang, X. Luo, Y. Qiu and Y. Zhang, “Transforensics: Image forgery detection through vision transformer,” in Proc. IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 4261–4270.
• S. Tariq, S. Lee, H. Kim, Y. Shin and S. S. Woo, “Detecting both machine and human created fake face images in the wild,” in Proc. ACMInternational Conference on Multimedia, 2018, pp. 1042–1050.
• R. Tolosana, R. Vera-Rodriguez, J. Fierrez, A. Morales and J. Ortega-Garcia, “Deepfakes and beyond: A survey of face manipulation and fake detection,” Information Fusion, vol. 64, pp. 131–148, 2020.