Intrusion detection in smart cities using Restricted Boltzmann Machines

Asmaa ELSAEIDY, Kumudu MUNASINGHE, Dharmendra SHARMA, Abbas JAMALIPOUR

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Smart cities have received greater attention over the recent years. Despite its popularity, unsecured smart city networks have become potential back door entry points. Distributed Denial of Service (DDoS) attacks are one of the most widespread threats to smart city infrastructure. In this paper, a smart city intrusion detection framework based on Restricted Boltzmann Machines (RBMs) is proposed. RBMs are applied due to their ability to learn high-level features from raw data in an unsupervised way and handle real data representation generated from smart meters and sensors. On top of these extracted features, different classifiers are trained. The performance of the proposed methodology is tested and benchmarked using a dataset from a smart water distribution plant. The results show the efficiency of the proposed methodology in attack detection with high accuracy. In addition, the proposed methodology outperforms the classification model applied without features learning step.

Original languageEnglish
Pages (from-to)76-83
Number of pages8
JournalJournal of Network and Computer Applications
Volume135
DOIs
Publication statusPublished - 2019

Fingerprint

Intrusion detection
Smart meters
Smart sensors
Classifiers
Smart city
Water

Cite this

@article{20a2df0166024e38bee4ac1071b2b445,
title = "Intrusion detection in smart cities using Restricted Boltzmann Machines",
abstract = "Smart cities have received greater attention over the recent years. Despite its popularity, unsecured smart city networks have become potential back door entry points. Distributed Denial of Service (DDoS) attacks are one of the most widespread threats to smart city infrastructure. In this paper, a smart city intrusion detection framework based on Restricted Boltzmann Machines (RBMs) is proposed. RBMs are applied due to their ability to learn high-level features from raw data in an unsupervised way and handle real data representation generated from smart meters and sensors. On top of these extracted features, different classifiers are trained. The performance of the proposed methodology is tested and benchmarked using a dataset from a smart water distribution plant. The results show the efficiency of the proposed methodology in attack detection with high accuracy. In addition, the proposed methodology outperforms the classification model applied without features learning step.",
keywords = "intrusion detection, Smart Cities, Restricted Boltzmann Machine",
author = "Asmaa ELSAEIDY and Kumudu MUNASINGHE and Dharmendra SHARMA and Abbas JAMALIPOUR",
year = "2019",
doi = "10.1016/j.jnca.2019.02.026",
language = "English",
volume = "135",
pages = "76--83",
journal = "Journal of Microcomputer Applications",
issn = "1084-8045",
publisher = "Academic Press Inc.",

}

Intrusion detection in smart cities using Restricted Boltzmann Machines. / ELSAEIDY, Asmaa; MUNASINGHE, Kumudu; SHARMA, Dharmendra; JAMALIPOUR, Abbas.

In: Journal of Network and Computer Applications, Vol. 135, 2019, p. 76-83.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Intrusion detection in smart cities using Restricted Boltzmann Machines

AU - ELSAEIDY, Asmaa

AU - MUNASINGHE, Kumudu

AU - SHARMA, Dharmendra

AU - JAMALIPOUR, Abbas

PY - 2019

Y1 - 2019

N2 - Smart cities have received greater attention over the recent years. Despite its popularity, unsecured smart city networks have become potential back door entry points. Distributed Denial of Service (DDoS) attacks are one of the most widespread threats to smart city infrastructure. In this paper, a smart city intrusion detection framework based on Restricted Boltzmann Machines (RBMs) is proposed. RBMs are applied due to their ability to learn high-level features from raw data in an unsupervised way and handle real data representation generated from smart meters and sensors. On top of these extracted features, different classifiers are trained. The performance of the proposed methodology is tested and benchmarked using a dataset from a smart water distribution plant. The results show the efficiency of the proposed methodology in attack detection with high accuracy. In addition, the proposed methodology outperforms the classification model applied without features learning step.

AB - Smart cities have received greater attention over the recent years. Despite its popularity, unsecured smart city networks have become potential back door entry points. Distributed Denial of Service (DDoS) attacks are one of the most widespread threats to smart city infrastructure. In this paper, a smart city intrusion detection framework based on Restricted Boltzmann Machines (RBMs) is proposed. RBMs are applied due to their ability to learn high-level features from raw data in an unsupervised way and handle real data representation generated from smart meters and sensors. On top of these extracted features, different classifiers are trained. The performance of the proposed methodology is tested and benchmarked using a dataset from a smart water distribution plant. The results show the efficiency of the proposed methodology in attack detection with high accuracy. In addition, the proposed methodology outperforms the classification model applied without features learning step.

KW - intrusion detection

KW - Smart Cities

KW - Restricted Boltzmann Machine

U2 - 10.1016/j.jnca.2019.02.026

DO - 10.1016/j.jnca.2019.02.026

M3 - Article

VL - 135

SP - 76

EP - 83

JO - Journal of Microcomputer Applications

JF - Journal of Microcomputer Applications

SN - 1084-8045

ER -