METHODOLOGICAL APPROACH TO COMPREHENSIVE IDENTIFICATION AND ANALYSIS OF CYBERTHREATS IN TRAFFIC IN 5G/IMT-2020 TELECOMMUNICATION NETWORKS BASED ON ARTIFICIAL INTELLIGENCE TECHNOLOGIES

Abstract

The paper analyzes the process of identifying and analyzing cyberthreats of incoming traffic in 5G/IMT-2020 networks built using Ultra-reliable and low latency communications technology, identifies its features and research directions for increasing the efficiency and monitoring of traffic and analyzing cyberthreats. To solve the problem of identifying traffic and analyzing cyberthreats in the 5G/IMT-2020 network, the paper develops and presents an appropriate methodological approach. The specified methodological approach includes formation of metadata arrays of the incoming flow of useful data and cyberattack data, modification of them into a set of training data, formation of a training software and hardware complex and development of the neural network structure, carrying out the process of training the neural network and implementing it in the process of traffic identification and analysis of cyber threats in 5G/IMT-2020 telecommunication networks.

Evaluation of the results of the training process of the proposed neural network and verification of its operation on test data sets in the trained state showed that the neural network presented in the work is able to monitor and identify traffic generated from Internet of Things services with a probability of up to 99.7%. In the process of monitoring and identifying traffic from two or more services, this probability may decrease, but is within the permissible limits of 80-90%.