AUTOMATION IS A PROCEDURE FOR DEEPFAKE IMAGE DETECTION USING NEURAL NETWORKS

About the magazine

Новости

oals and sphere

Founder and publisher

Editorial Board

Licensing conditions

Confidentiality

Attitude towards plagiarism

Publication ethics

Archiving Policy

Subscription

For authors

Instructions for authors

The review process

Copyright

Agreement on the transfer of rights

Editorial fees

Archive

All issues

Search

Contacts

Contacts

Babicheva M. V.
Candidate of Technical Sciences, Associate Professor of the Department of Radiophysics and Infocommunication Technologies
Donetsk State University, 24 Universitetskaya str., 283001, Donetsk,
Research interests: information security, pentesting, neural networks.

Tretyakov I. A.
Candidate of Technical Sciences, Associate Professor, Associate Professor of the Department of Radiophysics and Infocommunication Technologies
Donetsk State University, 24 Universitetskaya str., 283001, Donetsk,
Research interests: automation of scientific research and automated systems; optical information technologies; methods and systems of information protection, information security.

Скачать pdf

UDC 004.932.2
DOI 10.24412/2413-7383-94-105
Language: Russian
Annotation: Deepfakes are often used as tools for committing crimes against individuals and states, necessitating technical means to determine the artificial origin of images. This study explores various approaches to detecting fake images, including texture analysis, neural networks, and anomaly detection algorithms. The goal of the research is to investigate methods of creating fake images, identify their distinguishing features, and develop a detection methodology using deep learning and neural networks. For generating deepfakes, a generative adversarial network (GAN) was employed, while a convolutional neural network (CNN) was used for recognition. The proposed model achieves 89% иaccuracy in detecting fake images, performing on par with most foreign counterparts.
Keywords: deepfakes, generative adversarial network (GAN), convolutional neural network (CNN), Error Level Analysis.

References:
1. Tretiakov, I. A. Issledovanie parametrov rekurrentnoi neironnoi seti dlia raspoznavaniia cheloveka po golosu v sistemakh bezopasnosti / I. A. Tretiakov. E. N. Kozhekina, A. E. Myshkin // Vestnik Donetskogo natsionalnogo universiteta. Seriia G:Tekhnicheskie nauki. – 2021. – № 4. – S. 24-36. – EDN YUMGIV.
2. Tretiakov, I. A. Tekstonezavisimaia identifikatsiia rechi v usloviiakh pomekh / I. A. Tretiakov, E. N. Kozhekina, V. I. Syrovatskii // Vestnik Donetskogo natsionalnogo universiteta. Seriia G: Tekhnicheskie nauki. – 2022. – № 2. – S. 64-77. – EDN LUBRVH.
3. Sheluhin, O. I. Comparative analysis of informative features quantity and composition selection methods for the computer attacks classification using the unsw-nb15 dataset / O. I. Sheluhin, V. P. Ivannikova // TComm. – 2020. – Vol. 14. – No. 10. – P. 53-60. – DOI: 10.36724/2072-8735-2020-14-10-53-6
4. Yang, W. Security detection of network intrusion: application of cluster analysis method / W. Yang // Computer Optics. – 2020. –Vol. 44. – No. 4. – P. 660-664. – DOI: 10.18287/2412-6179-CO-657.
5. Klassifikatsiia mekhanizmov atak i issledovanie metodov zashchity sistem s ispolzovaniem algoritmov mashinnogo obucheniia i iskusstvennogo intellekta / I. V. Volodin, M. M. Putiato, A. S. Makarian, V. IU. Evglevskii // Prikaspiiskii zhurnal upravlenie i vysokie tekhnologii. – 2021. – № 2(54). – S. 91-98. – DOI 10.21672/2074-1707.2021.53.1.090-098. – EDN KWWOSM.
6. Babicheva, M.V. Primenenie metodov mashinnogo obucheniia dlia avtomatizirovannogo obnaruzheniia setevykh vtorzhenii / M. V. Babicheva, I. A. Tretiakov // Vestnik Dagestanskogo gosudarstvennogo tekhnicheskogo universiteta. Tekhnicheskie nauki. – 2023. – T. 50, № 1. – С. 53-61. – DOI 10.21822/2073- 6185-2023-50-1-53-61. – EDN MGBAGF.
7. Tretiakov, I. A. Prokhozhdenie CAPTCHA posredstvom mashinnogo obucheniia / I. A. Tretiakov, M. V. Babicheva, K. E. Lebedev // Iskusstvennyi intellect: teoreticheskie aspekty i prakticheskoe primenenie: materialy Donetskogo mezhdunarodnogo nauchnogo kruglogo stola (Donetsk, 30 may 2024). – Donetsk: FGBNU «Institut problem iskusstvennogo intellekta», 2024. – S. 254-260.
8. Ermolenko, T. V. Filtratsiia spama metodami glubokogo obucheniia / T. V. Ermolenko, N. A. SHalun // Vestnik Donetskogo natsionalnogo universiteta. Seriia G: Tekhnicheskie nauki. – 2024. – № 4. – С. 165- 174. – DOI 10.5281/zenodo.14514835. – EDN ECVVBZ.
9. Dovgal, V. A. Primenenie glubokogo obucheniia dlia sozdaniia i obnaruzheniia poddelnykh izobrazhenii sintezirovannykh s pomoshchiu iskusstvennogo intellekta / V. A. Dovgal // Vestnik Adygeiskogo gosudarstvennogo universiteta. Seriia 4: Estestvenno-matematicheskie i tekhnicheskie nauki. – 2021. – № 4(291). – S. 82-94. – DOI 10.53598/2410-3225-2021-4-291-82-94. – EDN PPECYM.
10. Dzhurov, A. A. Programmnoe sredstvo opredeliaiushchee feikovyi videokontent s pomoshchiu tekhnologii Deepfake algoritma GAN / A. A. Dzhurov, L. V. CHerkesova, E. A. Reviakina // Naukoemkie tekhnologii v kosmicheskikh issledovaniiakh Zemli. – 2023. – Т. 15, № 4. – S. 60-67. – DOI 10.36724/2409-5419- 2023-15-4-60-67. – EDN GOAPYT.
11. Alpatov, A. N. Arkhitektura trekhmernoi svertochnoi neironnoi seti dlia detektirovaniia fakta falsifikatsii videoriada / A. N. Alpatov, E. Z. Terloev, V. T. // Matchin Programmnye sistemy i vychislitelnye metody. – 2024. – № 3. – S 1-11. – DOI 10.7256/2454-0714.2024.3.70849. – EDN MNOVWB.
12. Zuev, V. M. Sravnenie obnaruzheniia obieektov sredstvami iskusstvennogo intellekta v sravnenii s klassicheskimi metodami / V. M. Zuev // Problemy iskusstvennogo intellekta. – 2024. – № 3(34). – S. 30- 35. – DOI 10.24412/2413-7383-2024-3-30-35. – EDN IIZDSH.
13. SHepel, N. V. Ispolzovanie vozmozhnostei iskusstvennogo intellekta pri sozdanii dipfeikov / N. V. SHepel, M. O. IAngaeva // Vestnik Sibirskogo iuridicheskogo instituta MVD Rossii. – 2024. – № 4(57). – S. 233- 239. – EDN INGWYS.
14. Krivoruchko, K. A. Raspoznavanie nedostovernoi informatsii v SMI s pomoshchiu neironnykh setei / K. A. Krivoruchko, I. I. Maksimenko // Vestnik Donetskogo natsionalnogo universiteta. Seriia G: Tekhnicheskie nauki. – 2024. – № 4. – S. 101-109. – DOI 10.5281/zenodo.14514617. – EDN ZTGSQR.
15. Putin's doppelganger asked Putin a question about doppelgangers and artificial intelligence [Electronic resource] – Electron, dan. – 2023. – Access mode: https://www.kp.ru/online/news/5589643/
16. Deepfake Image Detection Using Anchored Pairwise Learning Approach [Electronic resource] – Electron, dan. – 2020. – Access mode: https://repository.tudelft.nl/islandora/object/uuid%3Aaa4c6431-6880-406c8429-af5b04bc3b05
17. FaceForensics++: Learning to Detect Manipulated Facial Images [Electronic resource] – Electron, dan. – 2020. – Access mode: https://arxiv.org/pdf/1901.08971.pdf
18. DeepFake Detection [Electronic resource] – Electron, dan. – 2020. – Access mode: https://adityaanil.github.io/DeepFake-Detection/
19. A Continuous Deepfake Detection Benchmark: Dataset, Methods, and Essentials [Electronic resource] – Electron, dan. – 2020. – Access mode: https://coral79 .github.io/CDDB_web/
20.Intel Newsroom Archive 2022 [Electronic resource] – Electron, dan. – 2022. – Access mode: https://www.intel.com/content/www/us/en/newsroom/news/intel-introduces-real-time-deepfakedetector.html#gs.80elpl
21. Sensity AI [Electronic resource] – Electron, dan. – 2018. – Access mode: https://www.cbinsights.com/company/deeptrace
22. Hsu, C.-C. Deep Fake Image Detection Based on Pairwise Learning. / C.-C. Hsu, Y.-X. Zhuang, Lee C.-Y. // Applied Sciences. – 2020. V 1. – 14 p. – DOI 10.3390/app10010370.
23. Deepfake Detection [Electronic resource] – Electron, dan. – 2022. – Access mode: https://ucladeepvision.github.io/CS188-Projects-2022Winter/2022/02/04/team18-deepfake-detection.html

Release: 1(36)'2025
Chapter: METHODS AND SYSTEMS OF INFORMATION PROTECTION, INFORMATION SECURITY
How to quote: M. V. Babicheva, I. A. Tretiakov. AUTOMATION IS A PROCEDURE FOR DEEPFAKE IMAGE DETECTION USING NEURAL NETWORKS // Проблемы искусственного интеллекта. 2025. №1.

Back to 1(36)'2025