Email this article Deepfake detection using an optimal ensemble of deep learning models
- Authors: Lapsar A.P.1, Pogulyay G.S.1
-
Affiliations:
- Rostov State University of Economics (RINH)
- Issue: Vol 32, No 3 (2026)
- Pages: 134-142
- Section: Modeling and optimization
- Published: 13.03.2026
- URL: https://journals.eco-vector.com/1684-6400/article/view/704118
- DOI: https://doi.org/10.17587/it.32.134-142
- ID: 704118
Cite item
Open Access
Access granted
Abstract
The article proposes a method for combined detection of deepfakes based on the ensemble of several deep learning models that differ as much as possible in their properties. The method involves the use of ResNet, EfficientNet and MobileNe models. The integral result of the combination is formed by averaging the partial detection probabilities. The results of an experimental study are presented, demonstrating the advantages of the synthesized method when working with heterogeneous types of deepfakes.
Full Text
About the authors
A. P. Lapsar
Rostov State University of Economics (RINH)
Author for correspondence.
Email: lapsar1958@mail.ru
Cand. of Tech. Sc., Associate Professor
Russian Federation, Rostov-on-DonG. S. Pogulyay
Rostov State University of Economics (RINH)
Email: gena.pogulyay.0000@mail.ru
Postgraduate
Russian Federation, Rostov-on-DonReferences
- Tolosana R., Vera-Rodriguez R., Fierrez J. et al. DeepFakes and Beyond: А Survey of Face Manipulation and Fake Detection, Information Fusion, 2020, vol. 64, pp. 131—148.
- Verdoliva L. Media Forensics and DeepFakes: An Overview, IEEE J. Selected Topics in Signal Processing, 2020, vol. 14, no. 5, pp. 910—932.
- Heusen L., Hassen S., Yoo C. Remote Photoplethysmography for DeepFake Face Detection, Pattern Recognition Letters, 2023, vol. 174, pp. 19—26.
- Mirsky Y., Lee W. The Creation and Detection of Deepfakes: А Survey, ACM Computing Surveys, 2021, vol. 54, no. 1, art. 85.
- Papadopoulos A., Verdoliva L. One-Class Domain Adaptation for Generic Deepfake Detection, Pattern Recognition, 2023, vol. 141, Art. 109584.
- Dang H., Liu F., Stehouwer L. et al. Accuracy vs. Efficiency Trade-off in DeepFake Detection, Proc. IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 2209—2218.
- Stennikov V. A., Barakhtenko E. A., Sokolov D. V., Mayorov G. S. Automation of calculations in the design of an integrated energy system based on its digital twin, Informacionnye Tehnologii, 2024, vol. 30, no. 3, pp. 140—149 (in Russian).
- Li Y., Yang X., Sun P. et al. Celeb-DF v2: А Large-Scale Dataset for DeepFake Forensics, Proc. IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 3207—3216.
- Guarnera L., Giudice O., Battiato S. GAN Fingerprints Identify DeepFake Images, Proc. IEEE/CVF Int. Conf. on Computer Vision Workshops (ICCV Workshops), 2021, pp. 122—131.
- Rössler A., Verdoliva L., Riess C. et al. FaceForensics++: Learning to Detect Manipulated Facial Images, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, vol. 43, no. 1, pp. 501—514.
- Zhuang J., Wang L., Liu Q. Exploring Self-Supervised Vision Transformers for DeepFake Detection, arXiv preprint arXiv:2405.00355, 2024, available at: https://arxiv.org/abs/2405.00355 (date of access: 25.05.2025).
- Mirsky Y., Kalbo N., Elovici Y. CTGAN-Fake: Cross-Domain Generalization for Deepfake Detection, IEEE Transactions on Information Forensics and Security, 2024, vol. 19, pp. 1700—1714.
- Haliassos A., Kommando J., Ma S. et al. LipForensics: Audio-Visual Deepfake Detection by Fusing Phonetic and Visual Traces, Proc. IEEE/CVF Int. Conf. on Computer Vision (ICCV), 2021, pp. 428—437.
- Koohpayegani S-A., Mannan U., Rastegari M. Self-Prior 3D GAN Forensics, Proc. 38th Neural Information Processing Systems Conf. (NeurIPS), 2024.
- Deng X., Momeni F. Masked Autoencoders Are Few-Shot Learners for DeepFake Forensics, Proc. European Conf. on Computer Vision (ECCV). 2022. (LNCS 13695), pp. 375—392.
- Han H., Noh H., Yoo C. Video Deepfake Detection Using Hybrid CNN-LSTM-Transformer Architecture, Multimedia Tools and Applications, 2024.
- Salibekyan S. M. Dataflow-driven translation of high-level languages, Informacionnye Tehnologii, 2024, vol. 30, no. 5, pp. 261—268 (in Russian).
- Bosse S., Garrido P. Benign vs. Malign: Real-Time Deepfake Detection on Mobile Devices, Proc. IEEE/CVF Conf. on Computer Vision and Pattern Recognition Workshops (CVPR Workshops), 2023, pp. 123—132.
- Korobkin D. M., Fomenkov S. A., Zlobin A. R., Vereshchak G. A. Formation of metrics of innovation potential and prospects of technological forecasting, Informacionnye Tehnologii, 2023, vol. 29, no. 4, pp. 215—223 (in Russian).
Supplementary files
