Authors : Lalam Sravani; Ch. Pardhiv Kumar; K. Leela Pramod Kumar; A. Venkatesh; B. Nithin

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/4jswna9r

Scribd : https://tinyurl.com/4zscrnr3

DOI : https://doi.org/10.38124/ijisrt/26apr2013

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : In emerging digital media, deepfake videos have already been shown to be an extremely dangerous source of threats to trust, since such technology can create manipulate digital content in videos and images which looks highly realistic. There is a possibility of employing synthetic videos that leads to malicious behavior, which is danger and fraud, so there is a need to introduce robust methods for detecting deepfakes. It should be noted that conventional approaches t detecting deepfakes tend to employ one form of CNN (Convolutional Neural Networks), for instance ResNet and EfficientNet, however, in practice, such algorithms may not be applicable due to large number of methods used for manipulating videos and images. In this study, we propose to employ a hybrid approach based on utilizing deep neural network for hybrid feature extraction to build a better detection system. Specifically, our proposed method involves analyzing both spatial and temporal features by using Swin transformer and Temporal transformer and we also include Frequency transformer.

Keywords : Deepfake Detection, Deep Learning, Swin Transformer, Temporal Transformer, Frequency Transformer, Feature Fusion, Video Classification.

References :

1. Soudy, Ahmed Hatem, et al. "Deepfake Detection Using Convolutional Vision Transformers and Convolutional Neural Networks." Neural Computing and Applications, vol. 36, no. 31, 8 Aug. 2024, pp. 19759-775, https://doi.org/10.1007/s00521-024-10255-y.
2. Gong, Liang, Xue Li, and P. H. J. Chong. "Swin-Fake: A Consistency Learning Transformer-Based Deepfake Video Detector." Electronics, vol. 13, no. 15, Aug. 2024, p. 3045, https://doi.org/10.3390/electronics13153045.
3. Gao, Jie, et al. "DeepFake Detection Based on High-Frequency Enhancement Network for Highly Compressed Content." Expert Systems with Applications, vol. 249, part A, Aug. 2024, p. 123732, https://doi.org/10.1016/j.eswa.2024.123732.
4. Luan, Tao, Guoqing Liang, and Pengfei Peng. "Interpretable DeepFake Detection Based on Frequency Spatial Transformer." International Journal of Emerging Technologies and Advanced Applications, vol. 1, Mar. 2024, pp. 19-25, https://doi.org/10.62677/IJETAA.2402108.
5. Sunil, Reshma, et al. "Exploring Autonomous Methods for Deepfake Detection: A Detailed Survey on Techniques and Evaluation." Heliyon, vol. 11, no. 3, Feb. 2025, p. e42273, https://doi.org/10.1016/j.heliyon.2025.e42273.
6. Li, Yi, et al. "A Generalizable Deepfake Detection Method Based on Local Spatial-Frequency Feature Fusion." Proceedings of the 2026 International Conference, Jan. 2026, pp. 9-15, https://doi.org/10.1145/3779153.3779155.
7. Hasanaath, Ahmed, et al. "FSBI: Deepfake Detection with Frequency Enhanced Self-Blended Images." Image and Vision Computing, vol. 154, Feb. 2025, p. 105418, https://doi.org/10.1016/j.imavis.2025.105418.
8. Yadav, Uma, et al. "A Hybrid Approach for Robust Deep Fake Image Detection Using Spatial and Frequency Domain Features." Engineering, Technology & Applied Science Research, vol. 15, no. 3, June 2025, pp. 22786-791, https://doi.org/10.48084/etasr.10458.
9. Chorage, S. S., et al. "Deepfake Detection Using Deep Learning." International Research Journal on Advanced Engineering Hub, vol. 3, no. 8, Aug. 2025, pp. 3427-31, https://doi.org/10.47392/IRJAEH.2025.0502.
10. Iliev, Alexander I. "Discovery of Deepfakes in Art." Digital Presentation and Preservation of Cultural and Scientific Heritage, vol. 15, Sept. 2025, pp. 55–64, https://doi.org/10.55630/dipp.2025.15.5.
11. Spatiotemporal Deepfake Video Detection: A Hybrid CNN-Transformer Approach with Frequency Analysis." 2025 IEEE International Conference on Information Reuse and Integration and Data Science (IRI), IEEE, Sept. 2025, https://doi.org/10.1109/IRI61234.2025.00012.
12. Usman, Muhammad, et al. "Lightweight and Hybrid Transformer-Based Solution for Quick and Reliable Deepfake Detection." Frontiers in Big Data, vol. 8, Mar. 2025, https://doi.org/10.3389/fdata.2025.1521653.
13. "HTMDF-DD: Hybrid Triple Modality Based Spatial–Temporal Features Early Fusion for Deepfake Detection." ResearchGate, Feb. 2026, https://www.researchgate.net/publication/400322321.