Explore the Evolution of Deepfake Detection Techniques, focusing on the Transition from Traditional Methods to Hybrid Deep Learning Approaches

Sahana Kumari B; Thyagaraju G S; Pradeep Rao K  B

doi:10.55524/ijirem.2025.12.5.7

Abstract

Deepfake videos, generated using advanced techniques like GANs and autoencoders, pose serious challenges to media authenticity, security, and public trust. These synthetic videos can convincingly alter facial expressions, speech, and identity, making detection increasingly difficult. Traditional unimodal detection methods—focused on either visual or audio cues—often fall short in handling the complexity and diversity of modern deepfakes.This review explores a hybrid deep learning and multimodal approach to deepfake video detection, which combines different learning paradigms (e.g., CNNs, RNNs, transformers) and fuses multiple data modalities such as visual, auditory, and physiological signals. By examining state-of-the-art models and their performance on datasets like FaceForensics++, DFDC, and Celeb-DF, we highlight how these integrated methods offer improved accuracy, robustness, and generalization.The review also addresses key challenges such as real-time detection, explainability, and adversarial robustness. Finally, it outlines future directions, emphasizing the development of lightweight, interpretable, and scalable detection systems. This work serves as a critical resource for advancing reliable deepfake detection technologies in an era of rapidly evolving synthetic media.

Keywords

Deepfake Detection, Hybrid Deep Learning, CNN-RNN, Multimodal approach.

References

Alanazi, S., Asif, S., & Moulitsas, I. (2024). Examining the Societal Impact and Legislative Requirements of Deepfake Technology: A Comprehensive Study. International Journal of Social Science and Humanity. Available from: https://doi.org/10.18178/ijssh.2024.14.2.1194
Shahriyar, S. A., & Wright, M. (2022). Evaluating Robustness of Sequence-based Deepfake Detector Models by Adversarial Perturbation. Available from: https://doi.org/10.1145/3494109.3527194
Shahzad, S. A., Hashmi, A., Peng, Y.-T., Tsao, Y., & Wang, H.-M. (2023). AV-Lip-Sync+: Leveraging AV-HuBERT to Exploit Multimodal Inconsistency for Video Deepfake Detection. arXiv.Org, abs/2311.02733. Available from: https://doi.org/10.48550/arxiv.2311.02733
Altamimi, S., & Salameh, W. A. (2024). Towards Analysis Detection of Deepfake Video via Deep Learning Models: A Review. 87–92. Available from: https://doi.org/10.1109/ijcc64742.2024.10847278
Gandhi, K., Kulkarni, P. A., Shah, T., Chaudhari, P., Narvekar, M., & Ghag, K. (2024). A Multimodal Framework for Deepfake Detection. Available from: https://doi.org/10.48550/arxiv.2410.03487
Lin, C., Lee, J.-C., Wang, S.-J., Chiang, C.-S., & Chou, C. (2024). Video Detection Method Based on Temporal and Spatial Foundations for Accurate Verification of Authenticity. Electronics, 13(11), 2132. Available from: https://doi.org/10.3390/electronics13112132
Improving Deepfake Video Detection Using Data Augmentation Techniques. (2022). Available from: https://doi.org/10.21203/rs.3.rs-1844392/v1
Murugan, M. A., Mathu, T., & Priya, S. J. (2024). Detecting Deepfake Videos using Face Recognition and Neural Networks. 289–293. Available from: https://doi.org/10.1109/icc-robins60238.2024.10534025
Bharadwaj, R., Ratnaparkhi, S., Rajpurohit, R., Rahate, K., Pandita, R., & Thosar, S. (2023). Deepfake detection for preventing Audio and Video frauds using Advanced Deep Learning Techniques. 1–7. Available from: https://doi.org/10.1109/iciics59993.2023.10421486
Rathoure, N., Pateriya, R. K., Bharot, N., & Verma, P. (2024). Combating deepfakes: a comprehensive multilayer deepfake video detection framework. Multimedia Tools and Applications. Available from: https://doi.org/10.1007/s11042-024-20012-5
Koçak, A., Alkan, M., & Ar?kan, S. (2024). Deepfake Video Detection Using Convolutional Neural Network Based Hybrid Approach. Politeknik Dergisi. Available from: https://doi.org/10.2339/politeknik.1523983
Singh, P., Chaudhary, K., Chaudhary, G., & Khari, M. (2022). A Machine Learning Approach to Detecting Deepfake Videos: An Investigation of Feature Extraction Techniques. Journal of Cybersecurity and Information Management, 9(2), 42–50. Available from: https://doi.org/10.54216/jcim.090204
Alhaji, H. S., Çelik, Y., & Goel, S. (2024). An Approach to Deepfake Video Detection Based on ACO-PSO Features and Deep Learning. Electronics, 13(12), 2398. Available from: https://doi.org/10.3390/electronics13122398
Shirley, C. P., Jingle, B. J., Abisha, M. B., Venkatesan, R., Ram R V, Y., & Elango, E. (2024). Deepfake Detection Using Multi-Modal Fusion Combined with Attention Mechanism. 1194–1199. Available from: https://doi.org/10.1109/icses63445.2024.10763221
Multimodal Graph Learning for Deepfake Detection. (2022). Available from: https://doi.org/10.48550/arxiv.2209.05419
Arini, A., Setyaningrum, A. H., & Saputro, A. E. (2024). Deepfake Video Classification Using Random Forest and Stochastic Gradient Descent with Triplet Loss Approach Algorithm. 1–6. Available from: https://doi.org/10.1109/citsm64103.2024.10775699
Jbara, W., & Soud, J. (2024). DeepFake Detection Based VGG-16 Model. 1–6. Available from: https://doi.org/10.1109/iccr61006.2024.10533024
Cocchi, F., Baraldi, L., Poppi, S., Cornia, M., & Cucchiara, R. (n.d.). Unveiling the Impact of Image Transformations on Deepfake Detection: An Experimental Analysis. 345–356. Available from: https://doi.org/10.1007/978-3-031-43153-1_29
Rathoure, N., Pateriya, R. K., Bharot, N., & Verma, P. (2024). Combating deepfakes: a comprehensive multilayer deepfake video detection framework. Multimedia Tools and Applications. Available from: https://doi.org/10.1007/s11042-024-20012-5
Hu, J., Liao, X., Liang, J., Zhou, W., & Qin, Z. (2022). FInfer: Frame Inference-Based Deepfake Detection for High-Visual-Quality Videos. Proceedings of the AAAI Conference on Artificial Intelligence, 36(1), 951–959. Available from: https://doi.org/10.1609/aaai.v36i1.19978
Sharma, V. K., Singh, S., & Caudron, Q. (2024). Combating Deepfakes Using an Integrated Framework for Audio and Video Deepfake Detection. Available from: https://doi.org/10.21203/rs.3.rs-4861782/v1
Singh, V., Agone, B., More, A. W., Mengawade, A., Deshmukh, A., & Badgujar, A. (2024). SAVANA- A Robust Framework for Deepfake Video Detection and Hybrid Double Paraphrasing with Probabilistic Analysis Approach for AI Text Detection. International Journal for Science Technology and Engineering, 12(11), 2074–2083. Available from: https://doi.org/10.22214/ijraset.2024.65526
Hernandez-Ortega, J., Tolosana, R., Fierrez, J., & Morales, A. (2020). DeepFakesON-Phys: DeepFakes Detection based on Heart Rate Estimation. arXiv: Computer Vision and Pattern Recognition. Available from: https://arxiv.org/abs/2010.00400
A New Approach to Detect Deepfake Video using Multi-Input Convolutional Neural Network. (2022). Available from: https://doi.org/10.1109/sti56238.2022.10103229
Mao, X., Sun, L., Zhang, H., & Zhang, S. (2023). A DeepFake Compressed Video Detection Method Based on Dense Dynamic CNN. 12604, 1260409. Available from: https://doi.org/10.1117/12.2674838
Lai, J., Huo, Y., Hou, R., & Wang, X. (2022). A Universal Detection Method for Adversarial Examples and Fake Images. Sensors, 22(9), 3445. Available from: https://doi.org/10.3390/s22093445
Wang, C., Zhao, C., & Hu, G. (2022). Multi-Definition Video Deepfake Detection via Semantics Reduction and Cross-Domain Training. IEEE International Conference on Multimedia and Expo, 1–6. Available from: https://doi.org/10.1109/ICME52920.2022.9859736
Lin, C., Lee, J.-C., Wang, S.-J., Chiang, C.-S., & Chou, C. (2024). Video Detection Method Based on Temporal and Spatial Foundations for Accurate Verification of Authenticity. Electronics, 13(11), 2132. Available from: https://doi.org/10.3390/electronics13112132
Rana, P., & Bansal, S. (2024). Exploring Deepfake Detection: Techniques, Datasets and Challenges. International Journal of Computing and Digital Systems. Available from: https://doi.org/10.12785/ijcds/160156
Altamimi, S., & Salameh, W. A. (2024). Towards Analysis Detection of Deepfake Video via Deep Learning Models: A Review. 87–92. Available from: https://doi.org/10.1109/ijcc64742.2024.10847278
Helode, A., Yadav, A., Verma, V. P., & Srinivasa, K. G. (2024). Fusion of Machine Learning and Deep Learning: A Hybrid Approach for Deepfake Detection. 1–6. Available from: https://doi.org/10.1109/icccnt61001.2024.10724874
Stankov, I., & Dulgerov, E. E. (2024). Detection of Deepfake Images and Videos Using SVM, CNN, and Hybrid Approaches. 1–5. Available from: https://doi.org/10.1109/et63133.2024.10721497
Singh, D., Singh, P., & Bhandari, R. (2024). Enhancing Deepfake Video Detection: A Hybrid CNN-LSTM Approach. 130–135. Available from: https://doi.org/10.1109/tiacomp64125.2024.00031
Dinçer, S., Ulutas, G., Ustubioglu, B., Tahaoglu, G., & Sklavos, N. (2024). Golden ratio based deep fake video detection system with fusion of capsule networks. Computers & Electrical Engineering. Available from: https://doi.org/10.1016/j.compeleceng.2024.109234

Cites this article as

S. K. B, T. G. S, P. R. K. . B, "Explore the Evolution of Deepfake Detection Techniques, focusing on the Transition from Traditional Methods to Hybrid Deep Learning Approaches", International Journal of Innovative Research in Engineering and Management (IJIREM), Vol-12, Issue-5, Page No-38-44, 2025. Available from: https://doi.org/10.55524/ijirem.2025.12.5.7

Corresponding Author

Sahana Kumari B

Assistant Professor ,Department of Computer Science and Engineering, Sri Dharmasthala Manjunatheshwara Institute of Technology, Ujire, Karnataka, India