Threat analysis of IoT networks using artificial neural network intrusion detection system

Research output: Contribution to conferencePaper

59 Citations (Scopus)

Abstract

The Internet of things (IoT) network is still in its infancy and has attracted much interest in many industrial sectors including medical fields, logistics tracking, smart cities and automobiles. However as a paradigm, it is susceptible to a range of significant intrusion threats. This paper presents a threat analysis of the IoT and uses an Artificial Neural Network (ANN) to combat these threats. A multi-level perceptron, a type of supervised ANN, is trained using an IoT Data set, then is assessed on its ability to thwart Distributed Denial of Service (DDoS/DoS) attacks. This paper focuses on the classification of normal and threat patterns on an IoT Network. The ANN procedure is validated against a simulated IoT network. The experimental results demonstrate 99.4% accuracy and can successfully detect various DDoS/DoS attacks.

Conference

ConferenceInternational Symposium on Networks, Computers and Communications
Abbreviated titleISNCC
CountryTunisia
CityHammamet
Period11/05/1613/05/16
Internet address

Fingerprint

Intrusion detection
Neural networks
Automobiles
Logistics
Internet of things
Denial-of-service attack

Keywords

  • security
  • neural networks
  • intrusion detection systems
  • internet of things
  • denial of service

Cite this

Hodo, E. K., Bellekens, X., Hamilton, A., Dubouilh, P-L., Iorkyase, E. T., Tachtatzis, C., & Atkinson, R. (2016). Threat analysis of IoT networks using artificial neural network intrusion detection system. Paper presented at International Symposium on Networks, Computers and Communications, Hammamet, Tunisia.
@conference{62afd1c02bf847289a888958ca6634d1,
title = "Threat analysis of IoT networks using artificial neural network intrusion detection system",
abstract = "The Internet of things (IoT) network is still in its infancy and has attracted much interest in many industrial sectors including medical fields, logistics tracking, smart cities and automobiles. However as a paradigm, it is susceptible to a range of significant intrusion threats. This paper presents a threat analysis of the IoT and uses an Artificial Neural Network (ANN) to combat these threats. A multi-level perceptron, a type of supervised ANN, is trained using an IoT Data set, then is assessed on its ability to thwart Distributed Denial of Service (DDoS/DoS) attacks. This paper focuses on the classification of normal and threat patterns on an IoT Network. The ANN procedure is validated against a simulated IoT network. The experimental results demonstrate 99.4{\%} accuracy and can successfully detect various DDoS/DoS attacks.",
keywords = "security, neural networks, intrusion detection systems, internet of things, denial of service",
author = "Hodo, {Elike Komi} and Xavier Bellekens and Andrew Hamilton and Pierre-Louis Dubouilh and Iorkyase, {Ephraim Tersoo} and Christos Tachtatzis and Robert Atkinson",
note = "(c) 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.; International Symposium on Networks, Computers and Communications, ISNCC ; Conference date: 11-05-2016 Through 13-05-2016",
year = "2016",
month = "5",
day = "14",
language = "English",
url = "http://www.isncc-conf.org/",

}

Hodo, EK, Bellekens, X, Hamilton, A, Dubouilh, P-L, Iorkyase, ET, Tachtatzis, C & Atkinson, R 2016, 'Threat analysis of IoT networks using artificial neural network intrusion detection system' Paper presented at International Symposium on Networks, Computers and Communications, Hammamet, Tunisia, 11/05/16 - 13/05/16, .

Threat analysis of IoT networks using artificial neural network intrusion detection system. / Hodo, Elike Komi; Bellekens, Xavier; Hamilton, Andrew; Dubouilh, Pierre-Louis; Iorkyase, Ephraim Tersoo; Tachtatzis, Christos; Atkinson, Robert.

2016. Paper presented at International Symposium on Networks, Computers and Communications, Hammamet, Tunisia.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Threat analysis of IoT networks using artificial neural network intrusion detection system

AU - Hodo, Elike Komi

AU - Bellekens, Xavier

AU - Hamilton, Andrew

AU - Dubouilh, Pierre-Louis

AU - Iorkyase, Ephraim Tersoo

AU - Tachtatzis, Christos

AU - Atkinson, Robert

N1 - (c) 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.

PY - 2016/5/14

Y1 - 2016/5/14

N2 - The Internet of things (IoT) network is still in its infancy and has attracted much interest in many industrial sectors including medical fields, logistics tracking, smart cities and automobiles. However as a paradigm, it is susceptible to a range of significant intrusion threats. This paper presents a threat analysis of the IoT and uses an Artificial Neural Network (ANN) to combat these threats. A multi-level perceptron, a type of supervised ANN, is trained using an IoT Data set, then is assessed on its ability to thwart Distributed Denial of Service (DDoS/DoS) attacks. This paper focuses on the classification of normal and threat patterns on an IoT Network. The ANN procedure is validated against a simulated IoT network. The experimental results demonstrate 99.4% accuracy and can successfully detect various DDoS/DoS attacks.

AB - The Internet of things (IoT) network is still in its infancy and has attracted much interest in many industrial sectors including medical fields, logistics tracking, smart cities and automobiles. However as a paradigm, it is susceptible to a range of significant intrusion threats. This paper presents a threat analysis of the IoT and uses an Artificial Neural Network (ANN) to combat these threats. A multi-level perceptron, a type of supervised ANN, is trained using an IoT Data set, then is assessed on its ability to thwart Distributed Denial of Service (DDoS/DoS) attacks. This paper focuses on the classification of normal and threat patterns on an IoT Network. The ANN procedure is validated against a simulated IoT network. The experimental results demonstrate 99.4% accuracy and can successfully detect various DDoS/DoS attacks.

KW - security

KW - neural networks

KW - intrusion detection systems

KW - internet of things

KW - denial of service

UR - http://www.wikicfp.com/cfp/servlet/event.showcfp?eventid=48300

M3 - Paper

ER -

Hodo EK, Bellekens X, Hamilton A, Dubouilh P-L, Iorkyase ET, Tachtatzis C et al. Threat analysis of IoT networks using artificial neural network intrusion detection system. 2016. Paper presented at International Symposium on Networks, Computers and Communications, Hammamet, Tunisia.