Multilayer Perceptron Neural Network for Detection of Encrypted VPN Network Traffic

Shane Miller, Kevin Curran, Tom Lunney

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

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
LanguageEnglish
Title of host publication IEEE International Conference on Cyber Situational Awareness, Data Analytics and Assessment (Cyber SA 2018)
Pages12
Number of pages20
DOIs
Publication statusPublished - 6 Jun 2018
Event IEEE International Conference on Cyber Situational Awareness, Data Analytics and Assessment (Cyber SA 2018) - Scotland, Glasgow, United Kingdom
Duration: 11 Jun 201812 Jun 2018

Conference

Conference IEEE International Conference on Cyber Situational Awareness, Data Analytics and Assessment (Cyber SA 2018)
CountryUnited Kingdom
CityGlasgow
Period11/06/1812/06/18

Fingerprint

Personal computing
Multilayer neural networks
Learning systems
Websites
Neural networks
Industry

Keywords

  • vpn
  • Neural Network
  • Encryption

Cite this

Miller, S., Curran, K., & Lunney, T. (2018). Multilayer Perceptron Neural Network for Detection of Encrypted VPN Network Traffic. In IEEE International Conference on Cyber Situational Awareness, Data Analytics and Assessment (Cyber SA 2018) (pp. 12) https://doi.org/10.1109/CyberSA.2018.8551395
Miller, Shane ; Curran, Kevin ; Lunney, Tom. / Multilayer Perceptron Neural Network for Detection of Encrypted VPN Network Traffic. IEEE International Conference on Cyber Situational Awareness, Data Analytics and Assessment (Cyber SA 2018). 2018. pp. 12
@inproceedings{7225b446b7264854b27eb5a1b7f7971f,
title = "Multilayer Perceptron Neural Network for Detection of Encrypted VPN Network Traffic",
abstract = "There has been a growth in popularity of privacy inthe personal computing space and this has influenced the ITindustry. There is more demand for websites to use more secureand privacy focused technologies such as HTTPS and TLS. Thishas had a knock-on effect of increasing the popularity of VirtualPrivate Networks (VPNs). There are now more VPN offerings thanever before and some are exceptionally simple to setup.Unfortunately, this ease of use means that businesses will have aneed to be able to classify whether an incoming connection to theirnetwork is from an original IP address or if it is being proxiedthrough a VPN. A method to classify an incoming connection is tomake use of machine learning to learn the general patterns of VPNand non-VPN traffic in order to build a model capable ofdistinguishing between the two in real time. This paper outlines aframework built on a multilayer perceptron neural network modelcapable of achieving this goal",
keywords = "vpn, Neural Network, Encryption",
author = "Shane Miller and Kevin Curran and Tom Lunney",
year = "2018",
month = "6",
day = "6",
doi = "10.1109/CyberSA.2018.8551395",
language = "English",
pages = "12",
booktitle = "IEEE International Conference on Cyber Situational Awareness, Data Analytics and Assessment (Cyber SA 2018)",

}

Miller, S, Curran, K & Lunney, T 2018, Multilayer Perceptron Neural Network for Detection of Encrypted VPN Network Traffic. in IEEE International Conference on Cyber Situational Awareness, Data Analytics and Assessment (Cyber SA 2018). pp. 12, IEEE International Conference on Cyber Situational Awareness, Data Analytics and Assessment (Cyber SA 2018), Glasgow, United Kingdom, 11/06/18. https://doi.org/10.1109/CyberSA.2018.8551395

Multilayer Perceptron Neural Network for Detection of Encrypted VPN Network Traffic. / Miller, Shane; Curran, Kevin; Lunney, Tom.

IEEE International Conference on Cyber Situational Awareness, Data Analytics and Assessment (Cyber SA 2018). 2018. p. 12.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Multilayer Perceptron Neural Network for Detection of Encrypted VPN Network Traffic

AU - Miller, Shane

AU - Curran, Kevin

AU - Lunney, Tom

PY - 2018/6/6

Y1 - 2018/6/6

N2 - There has been a growth in popularity of privacy inthe personal computing space and this has influenced the ITindustry. There is more demand for websites to use more secureand privacy focused technologies such as HTTPS and TLS. Thishas had a knock-on effect of increasing the popularity of VirtualPrivate Networks (VPNs). There are now more VPN offerings thanever before and some are exceptionally simple to setup.Unfortunately, this ease of use means that businesses will have aneed to be able to classify whether an incoming connection to theirnetwork is from an original IP address or if it is being proxiedthrough a VPN. A method to classify an incoming connection is tomake use of machine learning to learn the general patterns of VPNand non-VPN traffic in order to build a model capable ofdistinguishing between the two in real time. This paper outlines aframework built on a multilayer perceptron neural network modelcapable of achieving this goal

AB - There has been a growth in popularity of privacy inthe personal computing space and this has influenced the ITindustry. There is more demand for websites to use more secureand privacy focused technologies such as HTTPS and TLS. Thishas had a knock-on effect of increasing the popularity of VirtualPrivate Networks (VPNs). There are now more VPN offerings thanever before and some are exceptionally simple to setup.Unfortunately, this ease of use means that businesses will have aneed to be able to classify whether an incoming connection to theirnetwork is from an original IP address or if it is being proxiedthrough a VPN. A method to classify an incoming connection is tomake use of machine learning to learn the general patterns of VPNand non-VPN traffic in order to build a model capable ofdistinguishing between the two in real time. This paper outlines aframework built on a multilayer perceptron neural network modelcapable of achieving this goal

KW - vpn

KW - Neural Network

KW - Encryption

U2 - 10.1109/CyberSA.2018.8551395

DO - 10.1109/CyberSA.2018.8551395

M3 - Conference contribution

SP - 12

BT - IEEE International Conference on Cyber Situational Awareness, Data Analytics and Assessment (Cyber SA 2018)

ER -

Miller S, Curran K, Lunney T. Multilayer Perceptron Neural Network for Detection of Encrypted VPN Network Traffic. In IEEE International Conference on Cyber Situational Awareness, Data Analytics and Assessment (Cyber SA 2018). 2018. p. 12 https://doi.org/10.1109/CyberSA.2018.8551395