RECOGNITION OF CYBER THREATS ON THE ADAPTIVE NETWORK TOPOLOGY OF LARGE-SCALE SYSTEMS BASED ON A RECURRENT NEURAL NETWORK

Abstract

The purpose of the article: the development of a method for recognizing cyber threats in adaptive network topologies of large-scale systems based on a recurrent neural network with a long short-term memory. Main research methods: system analysis of existing recognition methods, theoretical formalization, experiment Result: The approach showed a satisfactory efficiency of cyber threat recognition, and the results of the research made it possible to put forward proposals for the further development of this area. Scientific novelty: A model of adaptive network topology is formulated and a new way of recognizing cyber threats on the adaptive network topology of large-scale systems is proposed.