Generalizable deepfake video detection for multimedia security via temporal–spatial artifact localization and adaptive sequence modelling
*Kavita LalCorresponding authorkavitaroy@gmail.comDepartment of Computer Science and EngineeringPoornima UniversityJaipur, Rajasthan, 302022, IndiaView full profile → , Savita Shiwanisavita.shiwani@poornima.edu.inDepartment of Computer Science and EngineeringPoornima UniversityJaipur, Rajasthan, 302022, IndiaView full profile → , Geeta Chhabra Gandhigeeta.gandhi@jaipur.manipal.eduDepartment of Computer ApplicationsManipal University JaipurJaipur, Rajasthan, 303007, IndiaView full profile →
* Corresponding author · click or hover a name for details
- Received:
- 01 Mar 2026
- Published Online:
- 31 Oct 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JIOS-2487
- Pages:
- 3597–3606
Abstract
Due to the rise in face manipulation algorithms, it is difficult to distinguish real videos from computer-generated videos. For this, the paper proposes HABSNet, a model that performs artifact localization and temporal consistency analysis. The facial regions identified by MTCNN are analysed by ResNeXt-50 backbone model with the help of two-stream attention mechanism for detecting blending and frequency artifacts, as well as a BiLSTM based inter-frame self-attention gate for detecting unnatural eye movements and head pose changes. Trained on the FaceForensics++ (C23) dataset, the HABSNet achieves an accuracy of 94.88% and generalizes well on Celeb-DF v2 (0.950) and DFDC (0.920). For multimedia security the proposed framework contributes by allowing identification of manipulated videos across varied deepfake generation techniques.
Keywords
Subject Classifications
References
[1] A. Rössler, D. Cozzolino, L. Verdoliva, C. Riess, J. Thies, and M. Nießner, “FaceForensics++: Learning to detect manipulated facial images,” in Proc. IEEE/CVF Int. Conf. Comput. Vis. (ICCV), pp. 1–11 (2019), doi: 10.1109/ICCV.2019.00009.
[2] Y. Li, X. Yang, P. Sun, H. Qi, and S. Lyu, “Celeb-DF: A large-scale challenging dataset for deepfake forensics,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 3207–3216 (2020), doi: 10.1109/CVPR42600.2020.00327.
[3] B. Dolhansky, J. Bitton, B. Pflaum, J. Lu, R. Howes, M. Wang, and C. Canton-Ferrer, “The DeepFake Detection Challenge (DFDC) dataset,” arXiv preprint arXiv:2006.07397 (2020), doi: 10.48550/arXiv.2006.07397.
[4] S. Xie, R. Girshick, P. Dollár, Z. Tu, and K. He, “Aggregated residual transformations for deep neural networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 5987–5995 (2017), doi: 10.1109/CVPR.2017.634.
[5] J. Thies, M. Zollhöfer, M. Stamminger, C. Theobalt, and M. Nießner, “Face2Face: Real-time face capture and reenactment of RGB videos,” Commun. ACM, vol. 62, no. 1, pp. 96–104 (Jan. 2019), doi: 10.1145/3292039.
[6] L. Li, J. Bao, T. Zhang, H. Yang, D. Chen, F. Wen, and B. Guo, “Face X-ray for more general face forgery detection,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)), pp. 5001–5010 (2020), doi: 10.1109/CVPR42600.2020.00505.
[7] S. Kalra, C. H. S. Kumar, Y. Sharma, and G. S. Chauhan, “FakeExpose: Uncovering the falsity of news by targeting the multimodality via transfer learning,” J. Inf. Optim. Sci., vol. 44, no. 3, pp. 301–314 (2023).
[8] S. Kalra, Y. Bansal, Y. Sharma, and G. S. Chauhan, “FakeSpotter: A blockchain-based trustworthy idea for fake news detection in social media,” J. Inf. Optim. Sci., vol. 44, no. 3, pp. 515–527 (2023), doi: 10.47974/JIOS-1411.
[9] V. Sapkal, P. Gupta, and A. B. Khan, “Deep learning-based phishing website identification system using CNN-LSTM classifier,” J. Inf. Optim. Sci., vol. 44, no. 3, pp. 315–330 (2023).
[10] S. Sharma and B. Sharma, “Optimized data analysis through hybrid approach over trusted security environment,” J. Inf. Optim. Sci., vol. 44, no. 3, pp. 331–340 (2023).
[11] A. Singh and P. K. Roy, “Blockchain for Secure Computing: Technologies, Challenges, and Future Scope,” Journal of Information and Optimization Sciences, vol. 47, no. 7, pp. 2535–2582 (Jul. 2026), doi: 10.47974/JIOS-1980.
