<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE root>
<article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:ali="http://www.niso.org/schemas/ali/1.0/" article-type="research-article" dtd-version="1.2" xml:lang="en"><front><journal-meta><journal-id journal-id-type="publisher-id">Informacionnye Tehnologii</journal-id><journal-title-group><journal-title xml:lang="en">Informacionnye Tehnologii</journal-title><trans-title-group xml:lang="ru"><trans-title>Информационные технологии</trans-title></trans-title-group></journal-title-group><issn publication-format="print">1684-6400</issn><publisher><publisher-name xml:lang="en">New Technologies Publishing House</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="publisher-id">704118</article-id><article-id pub-id-type="doi">10.17587/it.32.134-142</article-id><article-categories><subj-group subj-group-type="toc-heading" xml:lang="en"><subject>Modeling and optimization</subject></subj-group><subj-group subj-group-type="toc-heading" xml:lang="ru"><subject>Моделирование и оптимизация</subject></subj-group><subj-group subj-group-type="article-type"><subject>Research Article</subject></subj-group></article-categories><title-group><article-title xml:lang="en">Deepfake detection using an optimal ensemble of deep learning models</article-title><trans-title-group xml:lang="ru"><trans-title>Детекция дипфейков с использованием оптимального ансамбля моделей глубокого обучения</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><name-alternatives><name xml:lang="en"><surname>Lapsar</surname><given-names>A. P.</given-names></name><name xml:lang="ru"><surname>Лапсарь</surname><given-names>А. П.</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>Cand. of Tech. Sc., Associate Professor</p></bio><bio xml:lang="ru"><p>канд. техн. наук, доц.</p></bio><email>lapsar1958@mail.ru</email><xref ref-type="aff" rid="aff1"/></contrib><contrib contrib-type="author"><name-alternatives><name xml:lang="en"><surname>Pogulyay</surname><given-names>G. S.</given-names></name><name xml:lang="ru"><surname>Погуляй</surname><given-names>Г. С.</given-names></name></name-alternatives><address><country country="RU">Russian Federation</country></address><bio xml:lang="en"><p>Postgraduate</p></bio><bio xml:lang="ru"><p>аспирант</p></bio><email>gena.pogulyay.0000@mail.ru</email><xref ref-type="aff" rid="aff1"/></contrib></contrib-group><aff-alternatives id="aff1"><aff><institution xml:lang="en">Rostov State University of Economics (RINH)</institution></aff><aff><institution xml:lang="ru">Ростовский государственный экономический университет (РИНХ)</institution></aff></aff-alternatives><pub-date date-type="pub" iso-8601-date="2026-03-13" publication-format="electronic"><day>13</day><month>03</month><year>2026</year></pub-date><volume>32</volume><issue>3</issue><issue-title xml:lang="en">Informacionnye Tehnologii</issue-title><issue-title xml:lang="ru">Информационные технологии</issue-title><fpage>134</fpage><lpage>142</lpage><history><date date-type="received" iso-8601-date="2026-03-11"><day>11</day><month>03</month><year>2026</year></date><date date-type="accepted" iso-8601-date="2026-03-11"><day>11</day><month>03</month><year>2026</year></date></history><permissions><copyright-statement xml:lang="en">Copyright ©; 2026, Informacionnye Tehnologii</copyright-statement><copyright-statement xml:lang="ru">Copyright ©; 2026, Информационные технологии</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="en">Informacionnye Tehnologii</copyright-holder><copyright-holder xml:lang="ru">Информационные технологии</copyright-holder></permissions><self-uri xlink:href="https://journals.eco-vector.com/1684-6400/article/view/704118">https://journals.eco-vector.com/1684-6400/article/view/704118</self-uri><abstract xml:lang="en"><p>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.</p></abstract><trans-abstract xml:lang="ru"><p>Предложен метод комбинированного выявления дипфейков, основанный на ансамблировании нескольких моделей глубокого обучения, максимально различающихся по своим свойствам. Метод предполагает использование моделей ResNet, EfficientNet и MobileNet, которые дополняют друг друга при детекции фальшивого контента. Интегральный результат объединения формируется путем усреднения частных вероятностей обнаружения. Показано, что ансамблирование повышает точность и надежность детекции дипфейков по сравнению с одиночными моделями. Приведены результаты экспериментального исследования, демонстрирующие заявленные преимущества синтезированного метода при работе с разнородными типами дипфейков.</p></trans-abstract><kwd-group xml:lang="en"><kwd>Deep learning</kwd><kwd>deepfake</kwd><kwd>fake detection</kwd><kwd>model combination</kwd><kwd>convolutional networks</kwd><kwd>ensemble learning</kwd><kwd>computer vision</kwd><kwd>model robustness</kwd><kwd>digital forensics</kwd></kwd-group><kwd-group xml:lang="ru"><kwd>глубокое обучение</kwd><kwd>дипфейк</kwd><kwd>детекция подделок</kwd><kwd>комбинирование моделей</kwd><kwd>сверточные сети</kwd><kwd>ансамблирование</kwd><kwd>компьютерное зрение</kwd><kwd>устойчивость модели</kwd><kwd>цифровая криминалистика</kwd></kwd-group><funding-group/></article-meta></front><body></body><back><ref-list><ref id="B1"><label>1.</label><citation-alternatives><mixed-citation xml:lang="en">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.</mixed-citation><mixed-citation xml:lang="ru">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. P. 131—148.</mixed-citation></citation-alternatives></ref><ref id="B2"><label>2.</label><citation-alternatives><mixed-citation xml:lang="en">Verdoliva L. Media Forensics and DeepFakes: An Overview, IEEE J. Selected Topics in Signal Processing, 2020, vol. 14, no. 5, pp. 910—932.</mixed-citation><mixed-citation xml:lang="ru">Verdoliva L. Media Forensics and DeepFakes: An Overview // IEEE J. Selected Topics in Signal Processing. 2020. Vol. 14, N. 5. P. 910—932.</mixed-citation></citation-alternatives></ref><ref id="B3"><label>3.</label><citation-alternatives><mixed-citation xml:lang="en">Heusen L., Hassen S., Yoo C. Remote Photoplethysmography for DeepFake Face Detection, Pattern Recognition Letters, 2023, vol. 174, pp. 19—26.</mixed-citation><mixed-citation xml:lang="ru">Heusen L., Hassen S., Yoo C. Remote Photoplethysmography for DeepFake Face Detection // Pattern Recognition Letters. 2023. Vol. 174. P. 19—26.</mixed-citation></citation-alternatives></ref><ref id="B4"><label>4.</label><citation-alternatives><mixed-citation xml:lang="en">14. Mirsky Y., Lee W. The Creation and Detection of Deepfakes: А Survey, ACM Computing Surveys, 2021, vol. 54, no. 1, art. 85.</mixed-citation><mixed-citation xml:lang="ru">Mirsky Y., Lee W. The Creation and Detection of Deepfakes: А Survey // ACM Computing Surveys. 2021. Vol. 54, N. 1. Art. 85.</mixed-citation></citation-alternatives></ref><ref id="B5"><label>5.</label><citation-alternatives><mixed-citation xml:lang="en">Papadopoulos A., Verdoliva L. One-Class Domain Adaptation for Generic Deepfake Detection, Pattern Recognition, 2023, vol. 141, Art. 109584.</mixed-citation><mixed-citation xml:lang="ru">Papadopoulos A., Verdoliva L. One-Class Domain Adaptation for Generic Deepfake Detection // Pattern Recognition. 2023. Vol. 141. Art. 109584.</mixed-citation></citation-alternatives></ref><ref id="B6"><label>6.</label><citation-alternatives><mixed-citation xml:lang="en">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.</mixed-citation><mixed-citation xml:lang="ru">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. P. 2209—2218.</mixed-citation></citation-alternatives></ref><ref id="B7"><label>7.</label><citation-alternatives><mixed-citation xml:lang="en">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).</mixed-citation><mixed-citation xml:lang="ru">Стенников В. А., Барахтенко Е. А., Соколов Д. В., Майоров Г. С. Автоматизация вычислений при проектировании интегрированной энергетической системы на основе ее цифрового двойника // Информационные технологии. 2024. Т. 30, № 3. С. 140—149.</mixed-citation></citation-alternatives></ref><ref id="B8"><label>8.</label><citation-alternatives><mixed-citation xml:lang="en">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.</mixed-citation><mixed-citation xml:lang="ru">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. P. 3207—3216.</mixed-citation></citation-alternatives></ref><ref id="B9"><label>9.</label><citation-alternatives><mixed-citation xml:lang="en">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.</mixed-citation><mixed-citation xml:lang="ru">Guarnera L., Giudice O., Battiato S. GAN Fingerprints Identify DeepFake Images // Proc. IEEE/CVF Int. Conf. on Computer Vision Workshops (ICCV Workshops). 2021. P. 122—131.</mixed-citation></citation-alternatives></ref><ref id="B10"><label>10.</label><citation-alternatives><mixed-citation xml:lang="en">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.</mixed-citation><mixed-citation xml:lang="ru">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, N. 1. P. 501—514.</mixed-citation></citation-alternatives></ref><ref id="B11"><label>11.</label><citation-alternatives><mixed-citation xml:lang="en">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).</mixed-citation><mixed-citation xml:lang="ru">Zhuang J., Wang L., Liu Q. Exploring Self-Supervised Vision Transformers for DeepFake Detection // arXiv preprint arXiv:2405.00355. 2024. URL: https://arxiv.org/abs/2405.00355 (дата обращения: 25.05.2025)</mixed-citation></citation-alternatives></ref><ref id="B12"><label>12.</label><citation-alternatives><mixed-citation xml:lang="en">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.</mixed-citation><mixed-citation xml:lang="ru">Mirsky Y., Kalbo N., Elovici Y. CTGAN-Fake: Cross-Domain Generalization for Deepfake Detection // IEEE Transactions on Information Forensics and Security. 2024. Vol. 19. P. 1700—1714.</mixed-citation></citation-alternatives></ref><ref id="B13"><label>13.</label><citation-alternatives><mixed-citation xml:lang="en">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.</mixed-citation><mixed-citation xml:lang="ru">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. P. 428—437.</mixed-citation></citation-alternatives></ref><ref id="B14"><label>14.</label><citation-alternatives><mixed-citation xml:lang="en">Koohpayegani S-A., Mannan U., Rastegari M. Self-Prior 3D GAN Forensics, Proc. 38th Neural Information Processing Systems Conf. (NeurIPS), 2024.</mixed-citation><mixed-citation xml:lang="ru">Koohpayegani S-A., Mannan U., Rastegari M. Self-Prior 3D GAN Forensics // Proc. 38th Neural Information Processing Systems Conf. (NeurIPS). 2024.</mixed-citation></citation-alternatives></ref><ref id="B15"><label>15.</label><citation-alternatives><mixed-citation xml:lang="en">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.</mixed-citation><mixed-citation xml:lang="ru">Deng X., Momeni F. Masked Autoencoders Are Few-Shot Learners for DeepFake Forensics // Proc. European Conf. on Computer Vision (ECCV). 2022. (LNCS13695). P. 375—392.</mixed-citation></citation-alternatives></ref><ref id="B16"><label>16.</label><citation-alternatives><mixed-citation xml:lang="en">Han H., Noh H., Yoo C. Video Deepfake Detection Using Hybrid CNN-LSTM-Transformer Architecture, Multimedia Tools and Applications, 2024.</mixed-citation><mixed-citation xml:lang="ru">Han H., Noh H., Yoo C. Video Deepfake Detection Using Hybrid CNN-LSTM-Transformer Architecture // Multimedia Tools and Applications. 2024.</mixed-citation></citation-alternatives></ref><ref id="B17"><label>17.</label><citation-alternatives><mixed-citation xml:lang="en">Salibekyan S. M. Dataflow-driven translation of high-level languages, Informacionnye Tehnologii, 2024, vol. 30, no. 5, pp. 261—268 (in Russian).</mixed-citation><mixed-citation xml:lang="ru">Салибекян С. М. Трансляция языков высокого уровня, управляемая потоками данных // Информационные технологии. 2024. Т. 30, № 5. С. 261—268.</mixed-citation></citation-alternatives></ref><ref id="B18"><label>18.</label><citation-alternatives><mixed-citation xml:lang="en">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.</mixed-citation><mixed-citation xml:lang="ru">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. P. 123—132.</mixed-citation></citation-alternatives></ref><ref id="B19"><label>19.</label><citation-alternatives><mixed-citation xml:lang="en">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).</mixed-citation><mixed-citation xml:lang="ru">Коробкин Д. М., Фоменков С. А., Злобин А. Р., Верещак Г. А. Формирование метрик инновационного потенциала и перспектив технологического прогнозирования // Информационные технологии. 2023. Т. 29, № 4. С. 215—223.</mixed-citation></citation-alternatives></ref></ref-list></back></article>
