System for in-depth analysis of network traffic based on artificial intelligence technologies

Abstract

The relevance of research is explained by the need to improve the network traffic analysis systems, including deep analysis systems, taking into account existing threats and vulnerabilities of network equipment and software of computer networks based on methods and algorithms of machine learning: • traffic analysis systems are widely used in monitoring network activity of some users or a specific user and restricting the client's access to certain types of services – VPN, HTTPS, which makes content analysis impossible; • such decisions may limit the access to prohibited resources in order to comply with legal requirements for methods of restricting access to information resources applied in accordance with the Federal Law “On Information, Information Technologies and Information Protection”. Network traffic analysis methods with the goal of defining an application layer protocol without traditional means of deep package inspection (DPI) are considered under conditions when the payload is encrypted (for example, TLS / SSL protocol). The novelty lies in the development of algorithms for analyzing network traffic on the basis of a neural network. This method differs in the way of features generation and selection, which allows classifying the existing traffic of protected connections of selected users according to a predefined set of categories. Keywords: Deep network traffic analysis, computer network, traffic encryption, VPN, neural network traffic analysis model, random trees committee