Перспективы использования машинного обучения для классификации сетевого трафика в технологиях доверенного взаимодействия

Abstract

The current stage of development of the world community is characterized by an everincreasing role of the information sphere and is completely dependent on information resources and technologies, their quality and security. Computerization of all aspects of life has become the main reason that a significant part of the elements of social relations cannot be implemented without the use of new IT in various subject areas, and hence without the implementation of a reliable system of integrated security of the developed information automated systems. This article gives the concept of network traffic, considers the classification of network traffic, in which classification by port numbers, deep packet analysis, stochastic packet analysis, and the use of machine learning were identified. Methods for protecting information using trusted technologies were defined, where a general presentation of trust technologies was considered. The main conclusions are drawn on the prospects of using machine learning to classify network traffic in trusted technologies.