Machine Learning Model of an Intelligent Decision Support System in the Information Security Sphere

Abstract

The article defines an approach to solving the task of network traffic analysis in higher education establishments (HEE) with the aim of detecting information security threats (IST) to systems, services, and networks. The approach implies using a machine learning model which utilizes neural network technology to classify running network activity as normal or abnormal, the two predetermined classes. In order to determine initial data for teaching and testing the machine learning model a specific approach was designed. The approach implies determination of a local network element, installation of necessary software, network analysis under the circumstances of normal network activity, network analysis under the circumstances of abnormal network activity, data processing and formation of a representative teaching selection.