MATHEMATICAL MODEL AND STRUCTURE OF A NEURAL NETWORK FOR DETECTION OF CYBER ATTACKS ON INFORMATION AND COMMUNICATION SYSTEMS

W artykule omówiono zasady tworzenia modelu matematycznego i architektury systemu poprzez zastosowanie metody sztucznej inteligencji do wykrywania cyberataków na systemy teleinformatyczne, gdzie wykorzystywana jest sieć neuronowa zdolna do uczenia się i wykrywania cyberataków. Proponowane podejście, oparte na zastosowaniu opracowanego modelu matematycznego i architektury sztucznych sieci neuronowych, jako detektora ataków sieciowych na systemy teleinformatyczne, pozwala na zwiększenie poziomu wykrywania włamań sieciowych do systemów komputerowych, zasobów sieciowych i internetowych. Zaproponowano algorytm przetwarzania parametrów ruchu sieciowego w systemach czasu rzeczywistego poprzez strukturyzację sieci neuronowej, co pozwala na optymalizację redundancji jej wielopoziomowej struktury na poziomie połączeń międzyelementowych.

Słowa kluczowe:

sieci neuronowe, ruch sieciowy, połączenie sieciowe, cyberatak, system teleinformatyczny

Bibliografia

[1] Andrushchenko M. et al.: Hand Movement Disorders Tracking By Smartphone Based On Computer Vision Methods. Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska – IAPGOS 14(2), 2024, 5–10 [https://doi.org/10.35784/iapgos.6126].

[2] Avrunin O. et al.: Improving the methods for visualization of middle ear pathologies based on telemedicine services in remote treatment. IEEE KhPI Week on Advanced Technology – KhPI Week 2020, 347–350 [https://doi:10.1109/KhPIWeek51551.2020.9250090].

[3] Bezobrazov S. et al.: Artificial intelligence for sport activitity recognition. 10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications – IDAACS 2019, V. 2, 628–632.

[4] Bisikalo O. et al.: Parameterization of the Stochastic Model for Evaluating Variable Small Data in the Shannon Entropy Basis. Entropy 25, 2023, 184 [https://doi.org/10.3390/e25020184].

[5] Dhangar K., Kulhare D., Khan A. A.: Proposed Intrusion Detection System. International Journal of Computer Applications 65(23), 2013, 46–50.

[6] Emelyanova Yu. G. et al.: Neural network technology for detecting network attacks on information resources. Software systems: theory and applications 3(7), 2011, 3–15.

[7] Haykin S.: Neural Networks and Learning Machines. Pearson Education, 2009.

[8] Kolodchak O. M.: Modern methods of detecting anomalies in intrusion detection systems. Bulletin of the Lviv Polytechnic National University. Series "Computer Systems and Networks" 745, 2012, 98–104.

[9] Korobiichuk I. et al.: Cyberattack classificator verification. Advanced Solutions in Diagnostics and Fault Tolerant Control, Springer International Publishing, 2018, 402–411.

[10] Lee J. et al.: Cyber Threat Detection Based on Artificial Neural Networks Using Event Profiles. IEEE Access 7, 2019, 165607–165626 [https://doi.org/10.1109/ACCESS.2019.2953095].

[11] Likhouzova T. A., Nosenko K. M., Pivtorak O. I.: Review of attack detection systems in network traffic. Adaptive automatic control systems 1(24), 2014, 67–75.

[12] Meleshko Ye.: Method of collaborative filtration based on associative networks of users similarity. Advanced information systems 2(4), 2018, 55–59.

[13] Naseer S., Saleem Y., Khalid S.: Enhanced network anomaly detection based on deep neural networks. IEEE Access 6, 2018, 48231–48246.

[14] Pakhomova V. M., Konnov M. S.: Research of two approaches to detect network attacks using neural network technologies. Science and Transport Progress 3(87), 2020, 81–93.

[15] Shestak Ya. et al.: Minimization of Information Losses in Data Centers as one of the Priority Areas of Information Security Technologies. IEEE 9th International Conference on Problems of Infocommunications, Science and Technology – PIC S&T, 2022, 227–230.

[16] Timchenko L. I. et al.: Approach to parallel-hierarchical network learning for real-time image sequences recognition, Proc. Machine Vision Systems for Inspection and Metrology VII, Boston (Massachusetts USA), 1999.

[17] Timchenko L. et al.: Q-processors for real-time image processing. Proc. SPIE 11581, 2020, 115810F.

[18] Turlykozhayeva D. et al.: Routing Algorithm for Software Defined Network Based on Boxcovering Algorithm. 10th International Conference on Wireless Networks and Mobile Communications – WINCOM, 2023.

[19] Turlykozhayeva D. et al.: Routing metric and protocol for wireless mesh network based on information entropy theory. Eurasian Physical Technical Journal 46, 2008, 90–98.

[20] Ulichev O. S. et al.: Computer modeling of dissemination of informational influences in social networks with different strategies of information distributors. Proc. SPIE 11176, 2019, 111761T.

[21] Wu Y., Wei D., Feng J.: Network Attacks Detection Methods Based on Deep Learning Techniques: A Survey, Wiley, Open Access, 2020 [https://doi.org/10.1155/2020/8872923].

[22] Zh Z. Z. et al.: Cluster router based on eccentricity, Eurasian Physical Technical Journal 19(3(41)), 2022, 84–90.

MODEL MATEMATYCZNY I STRUKTURA SIECI NEURONOWEJ DO WYKRYWANIA CYBERATAKÓW NA SYSTEMY TELEINFORMATYCZNE I KOMUNIKACYJNE. (2024). Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska, 14(3), 49-55. https://doi.org/10.35784/iapgos.6155

##plugins.themes.bootstrap3.article.sidebar##

Numer Tom 14 Nr 3 (2024)

Archiwum

##plugins.themes.bootstrap3.article.main##

Authors

Abstrakt

Słowa kluczowe:

Bibliografia

##plugins.themes.bootstrap3.article.details##

Licencja