Intrusion Detection System for Internet of Things based on a Machine Learning approach

Chao Liang, Bharanidharan Shanmugam, Sami Azam, Mirjam Jonkman, Friso De Boer, Ganthan Narayansamy

Research output: Chapter in Book/Report/Conference proceedingConference Paper published in ProceedingsResearchpeer-review

Abstract

With the application of Internet of Things technology to every aspect of life, the potential damage caused by Internet of things attacks is more serious than for traditional network attacks. Traditional intrusion detection systems do not serve the network environment of the IoT very well, so it is important to study intrusion detection systems suitable for the network environment of the Internet of Things. Researchers have found that the combination of machine learning technologies with an intrusion detection system is an effective way to resolve the drawbacks traditional IDSs have when they are used for IoT. This research involves the design of a novel intrusion detection system and the implementation and evaluation of its analysis model. This new intrusion detection system uses a hybrid placement strategy based on a multi-agent system. The new system consists of a data collection module, a data management module, an analysis module and a response module. For the implementation of the analysis module, this research applies a deep neural network algorithm for intrusion detection. The results demonstrate the efficiency of deep learning algorithms for detecting attacks from the transport layer. Compared with traditional detection methods used in IDSs, the analysis indicates that deep learning algorithms are more suitable for intrusion detection in an IoT network environment.

Original languageEnglish
Title of host publicationProceedings - International Conference on Vision Towards Emerging Trends in Communication and Networking, ViTECoN 2019
PublisherIEEE, Institute of Electrical and Electronics Engineers
ISBN (Electronic)9781538693537
DOIs
Publication statusPublished - 1 Mar 2019
Event2019 International Conference on Vision Towards Emerging Trends in Communication and Networking, ViTECoN 2019 - Vellore, Tamilnadu, India
Duration: 30 Mar 201931 Mar 2019

Publication series

NameProceedings - International Conference on Vision Towards Emerging Trends in Communication and Networking, ViTECoN 2019

Conference

Conference2019 International Conference on Vision Towards Emerging Trends in Communication and Networking, ViTECoN 2019
CountryIndia
CityVellore, Tamilnadu
Period30/03/1931/03/19

Fingerprint

Intrusion detection
Learning systems
Learning algorithms
Internet of things
Multi agent systems
Information management

Cite this

Liang, C., Shanmugam, B., Azam, S., Jonkman, M., Boer, F. D., & Narayansamy, G. (2019). Intrusion Detection System for Internet of Things based on a Machine Learning approach. In Proceedings - International Conference on Vision Towards Emerging Trends in Communication and Networking, ViTECoN 2019 [8899448] (Proceedings - International Conference on Vision Towards Emerging Trends in Communication and Networking, ViTECoN 2019). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ViTECoN.2019.8899448
Liang, Chao ; Shanmugam, Bharanidharan ; Azam, Sami ; Jonkman, Mirjam ; Boer, Friso De ; Narayansamy, Ganthan. / Intrusion Detection System for Internet of Things based on a Machine Learning approach. Proceedings - International Conference on Vision Towards Emerging Trends in Communication and Networking, ViTECoN 2019. IEEE, Institute of Electrical and Electronics Engineers, 2019. (Proceedings - International Conference on Vision Towards Emerging Trends in Communication and Networking, ViTECoN 2019).
@inproceedings{113eb61b0300445699147d3089f533e1,
title = "Intrusion Detection System for Internet of Things based on a Machine Learning approach",
abstract = "With the application of Internet of Things technology to every aspect of life, the potential damage caused by Internet of things attacks is more serious than for traditional network attacks. Traditional intrusion detection systems do not serve the network environment of the IoT very well, so it is important to study intrusion detection systems suitable for the network environment of the Internet of Things. Researchers have found that the combination of machine learning technologies with an intrusion detection system is an effective way to resolve the drawbacks traditional IDSs have when they are used for IoT. This research involves the design of a novel intrusion detection system and the implementation and evaluation of its analysis model. This new intrusion detection system uses a hybrid placement strategy based on a multi-agent system. The new system consists of a data collection module, a data management module, an analysis module and a response module. For the implementation of the analysis module, this research applies a deep neural network algorithm for intrusion detection. The results demonstrate the efficiency of deep learning algorithms for detecting attacks from the transport layer. Compared with traditional detection methods used in IDSs, the analysis indicates that deep learning algorithms are more suitable for intrusion detection in an IoT network environment.",
keywords = "Blockchain, Component, Cybersecurity, Intrusion Detection System, IoT, Machine Learning, Multi-agent system",
author = "Chao Liang and Bharanidharan Shanmugam and Sami Azam and Mirjam Jonkman and Boer, {Friso De} and Ganthan Narayansamy",
year = "2019",
month = "3",
day = "1",
doi = "10.1109/ViTECoN.2019.8899448",
language = "English",
series = "Proceedings - International Conference on Vision Towards Emerging Trends in Communication and Networking, ViTECoN 2019",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
booktitle = "Proceedings - International Conference on Vision Towards Emerging Trends in Communication and Networking, ViTECoN 2019",
address = "United States",

}

Liang, C, Shanmugam, B, Azam, S, Jonkman, M, Boer, FD & Narayansamy, G 2019, Intrusion Detection System for Internet of Things based on a Machine Learning approach. in Proceedings - International Conference on Vision Towards Emerging Trends in Communication and Networking, ViTECoN 2019., 8899448, Proceedings - International Conference on Vision Towards Emerging Trends in Communication and Networking, ViTECoN 2019, IEEE, Institute of Electrical and Electronics Engineers, 2019 International Conference on Vision Towards Emerging Trends in Communication and Networking, ViTECoN 2019, Vellore, Tamilnadu, India, 30/03/19. https://doi.org/10.1109/ViTECoN.2019.8899448

Intrusion Detection System for Internet of Things based on a Machine Learning approach. / Liang, Chao; Shanmugam, Bharanidharan; Azam, Sami; Jonkman, Mirjam; Boer, Friso De; Narayansamy, Ganthan.

Proceedings - International Conference on Vision Towards Emerging Trends in Communication and Networking, ViTECoN 2019. IEEE, Institute of Electrical and Electronics Engineers, 2019. 8899448 (Proceedings - International Conference on Vision Towards Emerging Trends in Communication and Networking, ViTECoN 2019).

Research output: Chapter in Book/Report/Conference proceedingConference Paper published in ProceedingsResearchpeer-review

TY - GEN

T1 - Intrusion Detection System for Internet of Things based on a Machine Learning approach

AU - Liang, Chao

AU - Shanmugam, Bharanidharan

AU - Azam, Sami

AU - Jonkman, Mirjam

AU - Boer, Friso De

AU - Narayansamy, Ganthan

PY - 2019/3/1

Y1 - 2019/3/1

N2 - With the application of Internet of Things technology to every aspect of life, the potential damage caused by Internet of things attacks is more serious than for traditional network attacks. Traditional intrusion detection systems do not serve the network environment of the IoT very well, so it is important to study intrusion detection systems suitable for the network environment of the Internet of Things. Researchers have found that the combination of machine learning technologies with an intrusion detection system is an effective way to resolve the drawbacks traditional IDSs have when they are used for IoT. This research involves the design of a novel intrusion detection system and the implementation and evaluation of its analysis model. This new intrusion detection system uses a hybrid placement strategy based on a multi-agent system. The new system consists of a data collection module, a data management module, an analysis module and a response module. For the implementation of the analysis module, this research applies a deep neural network algorithm for intrusion detection. The results demonstrate the efficiency of deep learning algorithms for detecting attacks from the transport layer. Compared with traditional detection methods used in IDSs, the analysis indicates that deep learning algorithms are more suitable for intrusion detection in an IoT network environment.

AB - With the application of Internet of Things technology to every aspect of life, the potential damage caused by Internet of things attacks is more serious than for traditional network attacks. Traditional intrusion detection systems do not serve the network environment of the IoT very well, so it is important to study intrusion detection systems suitable for the network environment of the Internet of Things. Researchers have found that the combination of machine learning technologies with an intrusion detection system is an effective way to resolve the drawbacks traditional IDSs have when they are used for IoT. This research involves the design of a novel intrusion detection system and the implementation and evaluation of its analysis model. This new intrusion detection system uses a hybrid placement strategy based on a multi-agent system. The new system consists of a data collection module, a data management module, an analysis module and a response module. For the implementation of the analysis module, this research applies a deep neural network algorithm for intrusion detection. The results demonstrate the efficiency of deep learning algorithms for detecting attacks from the transport layer. Compared with traditional detection methods used in IDSs, the analysis indicates that deep learning algorithms are more suitable for intrusion detection in an IoT network environment.

KW - Blockchain

KW - Component

KW - Cybersecurity

KW - Intrusion Detection System

KW - IoT

KW - Machine Learning

KW - Multi-agent system

UR - http://www.scopus.com/inward/record.url?scp=85075821103&partnerID=8YFLogxK

U2 - 10.1109/ViTECoN.2019.8899448

DO - 10.1109/ViTECoN.2019.8899448

M3 - Conference Paper published in Proceedings

T3 - Proceedings - International Conference on Vision Towards Emerging Trends in Communication and Networking, ViTECoN 2019

BT - Proceedings - International Conference on Vision Towards Emerging Trends in Communication and Networking, ViTECoN 2019

PB - IEEE, Institute of Electrical and Electronics Engineers

ER -

Liang C, Shanmugam B, Azam S, Jonkman M, Boer FD, Narayansamy G. Intrusion Detection System for Internet of Things based on a Machine Learning approach. In Proceedings - International Conference on Vision Towards Emerging Trends in Communication and Networking, ViTECoN 2019. IEEE, Institute of Electrical and Electronics Engineers. 2019. 8899448. (Proceedings - International Conference on Vision Towards Emerging Trends in Communication and Networking, ViTECoN 2019). https://doi.org/10.1109/ViTECoN.2019.8899448