A method for detecting network steganography based on machine learning

Krasov Andrey Vladimirovich

Classification of steganographic methods of information transformation is described in the basic model of threats to the security of personal data during their processing in personal data information systems, approved by the FSTEC of the Russian Federation in 2008. Due to the growing need for confidentiality in data transmission over modern communication channels, the popularity of various methods of steganography has increased. However, the development of methods of covert transmission of information has led to the need to identify participants in the illegal dissemination of information. This article discusses the possibility of analyzing network traffic using machine learning technologies. The article presents the results of work on the Grant-I B5/2020 project, proposals for improving the basic model.

Keywords:machine learning, steganography, TCP, ICMP, Bayesian networks.