MODELS FOR ENHANCED PROTECTION OF PERSONAL DATA OF USERS OF THE DISTANCE LEARNING SYSTEM OF THE ARMED FORCES OF UKRAINE

DOI: 10.31673/2412-4338.2022.023345

Abstract

The problem of improving existing and developing new models and methods of increasing the security of personal data of users of the distance learning system of the Armed Forces of Ukraine based on artificial intelligence is substantiated. It has been proven that to ensure a high level of security of personal data of users of distance learning systems in modern conditions, progressive organizational, hardware and software solutions are actively used. An analysis of foreign and domestic experience in the development and implementation of personal data protection systems for users of the distance learning system is provided, and a conclusion is made about the possibility of significantly increasing their efficiency due to the development of mathematical and software. It is justified that the most relevant in this direction is the use of models and methods of artificial intelligence, namely, fuzzy logic and hybrid networks. Research materials are presented on the development of a methodology for improving the security of personal data of users of the distance learning system of the Armed Forces of Ukraine, which provides an effective response to the flow of threats and is based on the implementation of models and methods of fuzzy logic and hybrid networks; the model for determining the state of the personal data protection system and the method of forecasting the state of the personal data protection system are described. The results of computer modeling are presented.

Keywords: protection, model, personal data, distance learning, fuzzy logic, hybrid network.

References
1. Savchenko V.,Matsko O.,Vorobiov O., Kizyak Y.Kriuchkova L.Tikhonov Y., Kotenko A. Network traffic forecasting based on the canonical expansion of a random process. Eastern European Journal of Enterprise Technologies. 2018. Vol 3, № 2 (93). pp. 33-41.
2. M. J. Hossain Faruk et al. Malware Detection and Prevention using Artificial Intelligence Techniques," 2021 IEEE International Conference on Big Data (Big Data), Orlando, FL, USA, 2021, pp. 5369-5377, doi: 10.1109/BigData52589.2021.9671434.
3. Rokon, M.O.F., Islam, R., Darki, A., Papalexakis, E., Faloutsos, M.: Sourcefinder: Finding malware source-code from publicly available repositories in github. No 10, 2020, pp. 149-163.
4. Shrestha, P., Maharjan, S., Ramirez-de-la Rosa, G., Sprague, A., Solorio, T., Warner,
G.: Using string information for malware family identification. No 11, 2014, pp. 686–697. https://doi.org/10.1007/978-3-319-12027-0 55
5. Schultz, M., Eskin, E., Zadok, F., Stolfo, S.: Data mining methods for detection of new malicious executables. No 02, 2001, pp. 38–49.
6. I. Baptista, S. Shiaeles and N. Kolokotronis, "A Novel Malware Detection System Based on Machine Learning and Binary Visualization," 2019 IEEE International Conference on Communications Workshops (ICC Workshops), Shanghai, China, 2019, pp. 1-6, doi: 10.1109/ICCW.2019.8757060.
7. Bose, S., Barao, T., Liu, X.: Explaining ai for malware detection: Analysis of mechanisms of malconv. In: 2020 International Joint Conference on Neural Networks (IJCNN). pp. 1-8.
8. Sharma, S., Challa, R., Sahay, S.: Detection of advanced malware by machine learning techniques. No 03, 2019.
9. Abhilash Chakraborty, Anupam Biswas, Ajoy Kumar Khan. Artificial Intelligence for Cybersecurity: Threats, Attacks and Mitigation. 2022. https://doi.org/10.48550/arXiv.2209.13454
10. Jang J.-S. R. ANFIS: Adaptive-Network-based Fuzzy Inference System. IEEE Transactions on Systems, Man, and Cybernetics: Systems. 1993. Vol. 23. no. 3. рр. 665−685.
11. Bohdan Zhurakovskyi, Serhii Toliupa, Volodymir Druzhynin, Andrii Bondarchuk, Mykhailo Stepanov . Calculation of Quality Indicators of the Future Multiservice Network. In: Future Intent-Based Networking: On the QoS Robust and Energy Efficient Heterogeneous Software Defined Networks. Springer International Publishing, 2022. p. 197-209.