Hibrit ResNeXt ve LSTM Mimarisi Kullanılarak Deepfake Video Algılama

Yıl 2025, ERKEN GÖRÜNÜM, 1 - 1

Nurcan Yardımcı , Mohamed Ibrahim Abdi , Burhan Ergen

https://doi.org/10.2339/politeknik.1721371

Öz

Deepfake içeriklerin artan yaygınlığı, bireysel gizlilik, medya güvenilirliği ve kamu güveni için ciddi bir tehdit oluşturmaktadır. Mevcut tespit yöntemleri genellikle çeşitli manipülasyon teknikleri ve video kalite seviyeleri arasında genelleme yapmakta zorlanmaktadır. Bu çalışma, ResNeXt-50'nin mekansal özellik çıkarma güçlerini LSTM ağlarının zamansal dizi modelleme yetenekleriyle birlikte kullanan derin öğrenmeye dayalı bir hibrit mimari sunmaktadır. Önerilen çerçeve, başlangıçta önceden eğitilmiş bir ResNeXt-50 omurgası aracılığıyla kare bazlı özellikler elde ederek ve ardından bir LSTM katmanı aracılığıyla zamansal dinamikleri inceleyerek video girişini işler. Deneysel değerlendirmeler, DFDC, Celeb-DF, FaceForensics++ ve DFD dahil olmak üzere kıyaslama veri kümeleri kullanılarak yürütülmüştür. Bulgular, geliştirilen modelin geleneksel CNN-LSTM kombinasyonlarından önemli ölçüde daha iyi performans gösterdiğini, DFDC veri kümesinde %95,7 ve diğer veri kümelerinde %90'ın üzerinde doğruluk elde ettiğini göstermektedir. Bu araştırma, hibrit derin öğrenme tekniklerinin gerçek dünya video kimlik doğrulama sistemlerinde pratik uygulanabilirliğini vurgulamakta ve sentetik ortam tespitinin büyüyen alanına yüksek performanslı bir çözüm sunmaktadır.

Anahtar Kelimeler

DeepFake , ResNeXt-50 , LSTM , Sahte Video Tespiti , Hibrit Derin Öğrenme

Deepfake Video Detection Using a Hybrid ResNeXt and LSTM Architecture

Öz

The growing spread of deepfake materials presents a serious threat to individual privacy, media credibility, and public trust. Existing detection methods often struggle to generalize across various manipulation techniques and video quality levels. This study proposes a hybrid A hybrid architecture based on deep learning is introduced, which leverages the spatial feature extraction strengths of ResNeXt-50 along with the temporal sequence modeling capabilities of LSTM networks. The suggested framework handles video input by initially obtaining frame-wise features via a pretrained ResNeXt-50 backbone and then examining temporal dynamics through an LSTM layer. Experimental evaluations were conducted using benchmark datasets, including DFDC, Celeb-DF, FaceForensics++, and DFD. Findings indicate that the developed model significantly outperforms conventional CNN-LSTM combinations, attaining 95.7% accuracy on the DFDC dataset and above 90% on the other datasets. This research highlights the practical applicability of hybrid deep learning techniques in real-world video authentication systems and contributes a high-performance solution to the growing field of synthetic media detection.

Anahtar Kelimeler

DeepFake , ResNeXt-50 , LSTM , Fake Video Detection , Hybrid Deep Learning

Kaynakça

• [1] Rani, E. G., Bhuvaneshwari, P., Darekar, R. G., and Anusha, D. “Enhanced deepfake video classification and detection: A ResNext-LSTM approach for improved accuracy”. In Data Science & Exploration in Artificial Intelligence, 468-476, (2025).
• [2] Petmezas, G., Vanian, V., Konstantoudakis, K., Almaloglou, E. E., and Zarpalas, D., “Video deepfake detection using a hybrid CNN-LSTM-Transformer model for identity verification”. Multimedia Tools and Applications, 1-20. (2025).
• [3] Xie, S., Girshick, R., Dollár, P., Tu, Z., and He, K., “Aggregated residual transformations for deep neural networks”, In Proceedings of the IEEE conference on computer vision and pattern recognition, 1492-1500, (2017).
• [4] Tan, M., and Le, Q., “Efficientnet: Rethinking model scaling for convolutional neural networks”, In International conference on machine learning, 6105-6114, PMLR, (2019).
• [5] He, K., Zhang, X., Ren, S., and Sun, J., “Deep residual learning for image recognition”, In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778), (2016).
• [6] Hochreiter, S., and Schmidhuber, J., “Long short-term memory”, Neural computation, 9(8), 1735-1780, (1997).
• [7] Donahue, J., Anne Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., and Darrell, T., “Long-term recurrent convolutional networks for visual recognition and description”, In Proceedings of the IEEE conference on computer vision and pattern recognition 2625-2634, (2015).
• [8] Saikia, P., Sharma, A., and Yadav, R., “A hybrid CNN-LSTM model for video deepfake detection by leveraging optical flow features”, arXiv preprint arXiv:2208.00788, (2022).
• [9] Koçak, A., Alkan, M., and Arıkan, S. M., “Deepfake Video Detection Using Convolutional Neural Network Based Hybrid Approach”, Politeknik Dergisi, 28(3), 957-968, (2025).
• [10] Sagar, N. K., and Arukonda, S., “A Novel CNN-LSTM Approach for Robust Deepfake Detection”, Procedia Computer Science, 258, 1844-1855, (2025).
• [11] Korkmaz, Ş., and Alkan, M., “Derin Öğrenme Algoritmalarını Kullanarak Deepfake Video Tespiti”, Politeknik Dergisi, 26(2), 855-862, (2023).
• [12] Devi, B. T., and Rajasekaran, R., “Deepfake Video Detection Using Ada-Boosting on the DFDC Dataset”, Procedia Computer Science, 258, 1091-1101, (2025).
• [13] Vamsi, V. V. V. N. S., Shet, S. S., Reddy, S. S. M., Rose, S. S., Shetty, S. R., Sathvika, S., and Shankar, S. P., “Deepfake detection in digital media forensics”, Global Transitions Proceedings, 3(1), (pp.74-79), (2022).
• [14] Antad, S., Arthamwar, V. V., Deshmukh, R. K., Chame, A. U., and Chhangani, H. P., “A Hybrid approach for DeepfakeDetection using CNN-RNN”, In 2024 OPJU International Technology Conference (OTCON) on Smart Computing for Innovation and Advancement in Industry 4.0, (pp. 1-6), IEEE, (2024).
• [15] Zhang, Y., Niu, R., Zhang, X., Chen, S., Wang, M., and Li, X. “Exploring coordinated motion patterns of facial landmarks for deepfake video detection”, Applied Soft Computing, 174, 112974, (2025).
• [16] Jayashre, K., and Amsaprabhaa, M., “Safeguarding media integrity: A hybrid optimized deep feature fusion based deepfake detection in videos”, Computers & Security, 142, 103860, (2024).
• [17] Selvaraj, P., Jagatheesaperumal, S. K., Marimuthu, K., Saravanan, O., Alkhamees, B. F., and Hassan, M. M., “Deepfake Detection Using Adversarial Neural Network”, Computer Modeling in Engineering & Sciences (CMES), 143(2), (2025).
• [18] Amritha Devi, N., and Simon, P., “DeepGuardNet: A Novel CNN Architecture for DeepFake Image Detection”, In Procedia Computer Science, 258, 811-818, Elsevier, (2025).
• [19] Kumar, N., and Kundu, A., “Cyber security focused deepfake detection system using big data”, SN Computer Science, 5(6), 752, (2024).
• [20] Li, Y., Yang, X., Sun, P., Qi, H., and Lyu, S., “Celeb-df: A large-scale challenging dataset for deepfake forensics”, In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 3207-3216, (2020).
• [21] Rossler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., and Nießner, M., “Faceforensics++: Learning to detect manipulated facial images”, In Proceedings of the IEEE/CVF international conference on computer vision, 1-11, (2019).
• [22] Dolhansky, B., Bitton, J., Pflaum, B., Lu, J., Howes, R., Wang, M., and Ferrer, C. C., “The deepfake detection challenge (dfdc) dataset”, arXiv preprint arXiv:2006.07397, (2020).