Algorithms for detecting network attacks in an enterprise industrial network based on data mining algorithms

Abstract

The article proposes the structure of a network traffic analysis system using machine learning models. The analysis of the specialized dataset WUSTL-IIOT-2018 was carried out, the main stages of data preprocessing, construction and testing of classifiers for detecting network attacks were performed. The possibility of embedding models as modules of specialized network equipment is proposed, which makes it possible to increase the efficiency of the analysis of network traffic, including specialized industrial protocols.