Analysis and Classification of Encrypted Network Traffic Using Machine Learning
Vladimir Muliukha, Leonid Laboshin, Alexey Lukashin, Nikolay V. Nashivochnikov
Abstract
This paper presents a prototype of an intelligent system for advanced analytics of encrypted traffic with the implementation of models and software developed in Peter the Great St. Petersburg Polytechnic University. Article presents methods for classifying encrypted traffic and examines the effectiveness of classifying applications in encrypted SSL sessions and determining user actions in VPN connections. The article presents the results of experimental studies of software that allows classification of encrypted traffic. The results of classification of VPN connections using the random forest algorithm are presented, as well as the results of classification of SSL traffic using naive Bayesian classifier.