Semi-supervised network traffic classification using deep generative models

Abstract

Network traffic classification plays a fundamental role in area of network management and security. Recent days, machine learning techniques have been used to classify network traffic. In particular, semi-supervised learning is very fit for practical scenarios, where pre-labelled training flows are hard to obtain. In this paper, a semi-supervised classification scheme is proposed for network traffic classification by using deep generative models. Specifically, the feature extractor module aims to automatically find representation features of raw traffic data in a lower dimensional feature space. Subsequently, using these representation features, a separated classifier is trained by the semi-supervised classification module. The method is verified with three different levels of datasets: Anomaly detection-level, protocol-level and application-level. The results show that our scheme can not only detect malware traffic, but also classify the traffic according to their protocol, application, and attack types. Using less than 20% labelled flows of the whole dataset, we can achieve the accuracy of over 95% which is a satisfying value compared with supervised learning method.