Multilayer Perceptron Neural Network for Detection of Encrypted VPN Network Traffic
Shane Miller, Kevin J Curran, Tom Lunney · 2018
There has been a growth in popularity of privacy in the personal computing space and this has influenced the IT industry. There is more demand for websites to use more secure and privacy focused technologies such as HTTPS and TLS. This has had a knock-on effect of increasing the popularity of Virtual Private Networks (VPNs). There are now more VPN offerings than ever before and some are exceptionally simple to setup. Unfortunately, this ease of use means that businesses will have a need to be able to classify whether an incoming connection to their network is from an original IP address or if it is being proxied through a VPN. A method to classify an incoming connection is to make use of machine learning to learn the general patterns of VPN and non-VPN traffic in order to build a model capable of distinguishing between the two in real time. This paper outlines a framework built on a multilayer perceptron neural network model capable of achieving this goal.