Email this article Ensuring security of data processing and transmission in promising wireless communication systems at the design stage using deep machine learning based on artificial intelligence
- Authors: Chirkov O.N.1, Antilikatorov A.B.1, Dushkin A.V.1,2, Shcherbakov V.A.2
-
Affiliations:
- Voronezh State Technical University
- National Research University of Electronic Technology (MIET)
- Issue: Vol 12, No 4 (2025)
- Pages: 124-130
- Section: METHODS AND SYSTEMS OF INFORMATION PROTECTION, INFORMATION SECURITY
- URL: https://medbiosci.ru/2313-223X/article/view/380193
- DOI: https://doi.org/10.33693/2313-223X-2025-12-4-124-130
- EDN: https://elibrary.ru/FYUXEJ
- ID: 380193
Cite item
Open Access
Access granted
Subscription Access
Abstract
Ensuring the security of data processing and transmission in advanced high-speed wireless communication systems is one of the priority tasks. This paper demonstrates that machine learning is widely used in the design of such systems at the upper layers of wireless communication systems. However, its application at the physical layer is hampered by complex channel environments and the limited learning capabilities of algorithms that describe the changing data transmission channel. This paper presents examples of applying deep machine learning methods at the physical layer to various wireless communication systems. Methods for creating a new architecture for remote access systems based on machine learning using an autoencoder are proposed. It is shown that the application of deep learning with artificial intelligence at the physical layer of wireless communication systems can facilitate the design of complex scenarios with unknown data transmission channel models. Algorithms based on deep machine learning with artificial intelligence demonstrate competitive performance with lower complexity or latency. They may find potential application in advanced secure high-speed, interference-resistant communication systems.
About the authors
Oleg N. Chirkov
Voronezh State Technical University
Author for correspondence.
Email: chir_oleg@mail.ru
ORCID iD: 0000-0003-2250-2100
SPIN-code: 4391-1330
senior lecturer, Department of Design and production of radio equipment
Russian Federation, VoronezhAleksandr B. Antilikatorov
Voronezh State Technical University
Email: antilikatorov63@mail.ru
SPIN-code: 7321-0897
Cand. Sci. (Eng.), Associate Professor, associate professor Department of Design and production of radio equipment
Russian Federation, VoronezhAlexander V. Dushkin
Voronezh State Technical University; National Research University of Electronic Technology (MIET)
Email: a_dushkin@mail.ru
ORCID iD: 0000-0002-8078-8971
SPIN-code: 9285-2678
Dr. Sci. (Eng.), Associate Professor, Professor Department of Information Security, Professor Department of Radio Engineering
Russian Federation, Voronezh; Zelenograd, MoscowVitaly A. Shcherbakov
National Research University of Electronic Technology (MIET)
Email: svasvarog@yandex.ru
SPIN-code: 5166-8727
Dr. Sci. (Eng.), Associate Professor, Professor, Department of Information Security
Russian Federation, Zelenograd, MoscowReferences
- O’Shea T.J., Hoydis J. An introduction to deep learning for the physical layer. IEEE Transactions on Cognitive Communications and Networking. 2017. Vol. 3. No. 4. Pp. 563–575.
- Chirkov O.N. An efficient algorithm for dynamic pilot signal distribution for radio channel estimation in multi-antenna MIMO systems with orthogonal frequency division multiplexing (OFDM). Radio Engineering. 2019. Vol. 83. No. 6 (8). Pp. 163–168. (In Rus.)
- Chirkov O.N., Bashkirov A.V. Improving the efficiency of channel estimation for high-speed data transmission in underwater acoustic communication with OFDM. Radio Engineering. 2024. Vol. 88. No. 7. Pp. 45–49. (In Rus.). doi: 10.18127/j00338486-202407-09.
- Chirkov O.N., Romashchenko M.A., Chepelev M.Yu. Modern methods for assessing a radio communication channel under multipath conditions. Bulletin of Voronezh State Technical University. 2019. Vol. 15. No. 3. Pp. 68–73. (In Rus.). doi: 10.25987/VSTU.2019.15.3.010.
- Daniels R.C., Caramanis C.M., Heath R.W. Adaptation in convolutionally coded MIMO-OFDM wireless systems through supervised learning and SNR ordering. IEEE Trans. Veh. Technol. 2010. Vol. 59. No. 1. Pp. 114–126.
- Fehske A., Gaeddert J., Reed J. A new approach to signal classification using spectral correlation and neural networks. In: Proc. IEEE Int. Symp. New Frontiers in Dynamic Spectrum Access Networks (DYSPAN). 2005. Pp. 144–150.
- Ibukahla M., Sombria J., Castanie F., Bershad N. Neural networks for modeling nonlinear memoryless communication channels. IEEE Trans. Commun. 1997. Vol. 45. No. 7. Pp. 768–771.
- Sviridova I.V., Bobylkin I.S., Chirkov O.N. Optimization of estimation of multipath radio communication channel with OFDM. In: Proceedings of the international symposium “Reliability and Quality”. 2018. Vol. 2. Pp. 131–133.
- Chen S., Gibson G., Cowan C., Grant P. Adaptive equalization of finite non-linear channels using multilayer perceptrons. Elsevier Signal Processing. 1990. Vol. 20. No. 2. Pp. 107–119.
- Hornik K., Stinchcombe M., White H. Multilayer feedforward networks are universal approximators. Neural Networks. 1989. Vol. 2. No. 5. Pp. 359–366.
- Kasatkina T.I., Rossikhina L.V., Dushkin A.V. et al. Application of neural network technology in the security subsystem of information systems. Devices and Systems. Management, Control, Diagnostics. 2019. No. 6. Pp. 31–38. (In Rus.). doi: 10.25791/pribor.06.2019.693.
- Dushkin A.V., Sokolovsky S.P. Neural network implementation of an unauthorized access detection module on special-purpose information and communication systems. Information and Security. 2010. No. 1. Pp. 123–126. (In Rus.)
- Chirkov O.N. Methods for assessing a communication channel with spatial modulation based on correlation. Bulletin of the Voronezh State Technical University. 2021. Vol. 17. No. 4. Pp. 106–110. (In Rus.)
- Chirkov O.N. Evaluation of the throughput of high-level types of m-QAM modulation. Bulletin of the Voronezh State Technical University. 2012. Vol. 8. No. 6. Pp. 12–13. (In Rus.)
Supplementary files
