No Cover Image

Journal article 250 views 28 downloads

PIGNUS: A Deep Learning Model for IDS in Industrial Internet-of-Things

P.L.S. Jayalaxmi, Rahul Saha, Gulshan Kumar, Mamoun Alazab, Mauro Conti Orcid Logo, Cheng Cheng Orcid Logo

Computers and Security, Volume: 132, Start page: 103315

Swansea University Author: Cheng Cheng Orcid Logo

  • 63596.pdf

    PDF | Accepted Manuscript

    Distributed under the terms of a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Licence (CC BY-NC-ND 4.0).

    Download (2.46MB)

Check full text

DOI (Published version): 10.1016/j.cose.2023.103315

Abstract

The heterogeneous nature of the Industrial Internet of Thing (IIoT) has a considerable impact on the development of an effective Intrusion Detection System (IDS). The proliferation of linked devices results in multiple inputs from industrial sensors. IDS faces challenges in analyzing the features of...

Full description

Published in: Computers and Security
ISSN: 0167-4048
Published: Elsevier BV 2023
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa63596
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2023-06-06T13:38:40Z
last_indexed 2023-06-06T13:38:40Z
id cronfa63596
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>63596</id><entry>2023-06-06</entry><title>PIGNUS: A Deep Learning Model for IDS in Industrial Internet-of-Things</title><swanseaauthors><author><sid>11ddf61c123b99e59b00fa1479367582</sid><ORCID>0000-0003-0371-9646</ORCID><firstname>Cheng</firstname><surname>Cheng</surname><name>Cheng Cheng</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2023-06-06</date><deptcode>MACS</deptcode><abstract>The heterogeneous nature of the Industrial Internet of Thing (IIoT) has a considerable impact on the development of an effective Intrusion Detection System (IDS). The proliferation of linked devices results in multiple inputs from industrial sensors. IDS faces challenges in analyzing the features of the traffic and identifying anonymous behavior. Due to the unavailability of a comprehensive feature mapping method, the present IDS solutions are non-usable to identify zero-day vulnerabilities.In this paper, we introduce the first comprehensive IDS framework that combines an efficient feature-mapping technique and cascading model to solve the above-mentioned problems. We call our proposed solution deeP learnIG model intrusioN detection in indUStrial internet-of things (PIGNUS). PIGNUS integrates Auto Encoders (AE) to select optimal features and Cascade Forward Back Propagation Neural Network (CFBPNN) for classification and attack detection. The cascading model uses interconnected links from the initial layer to the output layer and determines the normal and abnormal behavior patterns and produces a perfect classification. We execute a set of experiments on five popular IIoT datasets: gas pipeline, water storage tank, NSLKDD+, UNSW-NB15, and X-IIoTID. We compare PIGNUS to the state-of-the-art models in terms of accuracy, False Positive Ratio (FPR), precision, and recall. The results show that PIGNUS provides more than 95% accuracy, which is 25% better on average than the existing models. In the other parameters, PIGNUS shows 20% improved FPR, 10% better recall, and 10% better in precision. Overall, PIGNUS proves its efficiency as an IDS solution for IIoTs. Thus, PIGNUS is an efficient solution for IIoTs.</abstract><type>Journal Article</type><journal>Computers and Security</journal><volume>132</volume><journalNumber/><paginationStart>103315</paginationStart><paginationEnd/><publisher>Elsevier BV</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint>0167-4048</issnPrint><issnElectronic/><keywords>IoT, Industry, Security, Intrusion, Detection</keywords><publishedDay>30</publishedDay><publishedMonth>9</publishedMonth><publishedYear>2023</publishedYear><publishedDate>2023-09-30</publishedDate><doi>10.1016/j.cose.2023.103315</doi><url/><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>This work was supported by the European Commission under the Horizon Europe Programme, as part of the project LAZARUS (https://lazarus-he.eu/) (Grant Agreement No. 101070303).</funders><projectreference/><lastEdited>2024-07-29T15:08:08.8121459</lastEdited><Created>2023-06-06T14:35:05.5385529</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>P.L.S.</firstname><surname>Jayalaxmi</surname><order>1</order></author><author><firstname>Rahul</firstname><surname>Saha</surname><order>2</order></author><author><firstname>Gulshan</firstname><surname>Kumar</surname><order>3</order></author><author><firstname>Mamoun</firstname><surname>Alazab</surname><order>4</order></author><author><firstname>Mauro</firstname><surname>Conti</surname><orcid>0000-0002-3612-1934</orcid><order>5</order></author><author><firstname>Cheng</firstname><surname>Cheng</surname><orcid>0000-0003-0371-9646</orcid><order>6</order></author></authors><documents><document><filename>63596__27729__3700964a09c743d9bccd80bbb4324736.pdf</filename><originalFilename>63596.pdf</originalFilename><uploaded>2023-06-07T08:55:59.0208843</uploaded><type>Output</type><contentLength>2580610</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2024-06-02T00:00:00.0000000</embargoDate><documentNotes>Distributed under the terms of a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Licence (CC BY-NC-ND 4.0).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by-nc-nd/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 63596 2023-06-06 PIGNUS: A Deep Learning Model for IDS in Industrial Internet-of-Things 11ddf61c123b99e59b00fa1479367582 0000-0003-0371-9646 Cheng Cheng Cheng Cheng true false 2023-06-06 MACS The heterogeneous nature of the Industrial Internet of Thing (IIoT) has a considerable impact on the development of an effective Intrusion Detection System (IDS). The proliferation of linked devices results in multiple inputs from industrial sensors. IDS faces challenges in analyzing the features of the traffic and identifying anonymous behavior. Due to the unavailability of a comprehensive feature mapping method, the present IDS solutions are non-usable to identify zero-day vulnerabilities.In this paper, we introduce the first comprehensive IDS framework that combines an efficient feature-mapping technique and cascading model to solve the above-mentioned problems. We call our proposed solution deeP learnIG model intrusioN detection in indUStrial internet-of things (PIGNUS). PIGNUS integrates Auto Encoders (AE) to select optimal features and Cascade Forward Back Propagation Neural Network (CFBPNN) for classification and attack detection. The cascading model uses interconnected links from the initial layer to the output layer and determines the normal and abnormal behavior patterns and produces a perfect classification. We execute a set of experiments on five popular IIoT datasets: gas pipeline, water storage tank, NSLKDD+, UNSW-NB15, and X-IIoTID. We compare PIGNUS to the state-of-the-art models in terms of accuracy, False Positive Ratio (FPR), precision, and recall. The results show that PIGNUS provides more than 95% accuracy, which is 25% better on average than the existing models. In the other parameters, PIGNUS shows 20% improved FPR, 10% better recall, and 10% better in precision. Overall, PIGNUS proves its efficiency as an IDS solution for IIoTs. Thus, PIGNUS is an efficient solution for IIoTs. Journal Article Computers and Security 132 103315 Elsevier BV 0167-4048 IoT, Industry, Security, Intrusion, Detection 30 9 2023 2023-09-30 10.1016/j.cose.2023.103315 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University This work was supported by the European Commission under the Horizon Europe Programme, as part of the project LAZARUS (https://lazarus-he.eu/) (Grant Agreement No. 101070303). 2024-07-29T15:08:08.8121459 2023-06-06T14:35:05.5385529 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science P.L.S. Jayalaxmi 1 Rahul Saha 2 Gulshan Kumar 3 Mamoun Alazab 4 Mauro Conti 0000-0002-3612-1934 5 Cheng Cheng 0000-0003-0371-9646 6 63596__27729__3700964a09c743d9bccd80bbb4324736.pdf 63596.pdf 2023-06-07T08:55:59.0208843 Output 2580610 application/pdf Accepted Manuscript true 2024-06-02T00:00:00.0000000 Distributed under the terms of a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Licence (CC BY-NC-ND 4.0). true eng http://creativecommons.org/licenses/by-nc-nd/4.0/
title PIGNUS: A Deep Learning Model for IDS in Industrial Internet-of-Things
spellingShingle PIGNUS: A Deep Learning Model for IDS in Industrial Internet-of-Things
Cheng Cheng
title_short PIGNUS: A Deep Learning Model for IDS in Industrial Internet-of-Things
title_full PIGNUS: A Deep Learning Model for IDS in Industrial Internet-of-Things
title_fullStr PIGNUS: A Deep Learning Model for IDS in Industrial Internet-of-Things
title_full_unstemmed PIGNUS: A Deep Learning Model for IDS in Industrial Internet-of-Things
title_sort PIGNUS: A Deep Learning Model for IDS in Industrial Internet-of-Things
author_id_str_mv 11ddf61c123b99e59b00fa1479367582
author_id_fullname_str_mv 11ddf61c123b99e59b00fa1479367582_***_Cheng Cheng
author Cheng Cheng
author2 P.L.S. Jayalaxmi
Rahul Saha
Gulshan Kumar
Mamoun Alazab
Mauro Conti
Cheng Cheng
format Journal article
container_title Computers and Security
container_volume 132
container_start_page 103315
publishDate 2023
institution Swansea University
issn 0167-4048
doi_str_mv 10.1016/j.cose.2023.103315
publisher Elsevier BV
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 1
active_str 0
description The heterogeneous nature of the Industrial Internet of Thing (IIoT) has a considerable impact on the development of an effective Intrusion Detection System (IDS). The proliferation of linked devices results in multiple inputs from industrial sensors. IDS faces challenges in analyzing the features of the traffic and identifying anonymous behavior. Due to the unavailability of a comprehensive feature mapping method, the present IDS solutions are non-usable to identify zero-day vulnerabilities.In this paper, we introduce the first comprehensive IDS framework that combines an efficient feature-mapping technique and cascading model to solve the above-mentioned problems. We call our proposed solution deeP learnIG model intrusioN detection in indUStrial internet-of things (PIGNUS). PIGNUS integrates Auto Encoders (AE) to select optimal features and Cascade Forward Back Propagation Neural Network (CFBPNN) for classification and attack detection. The cascading model uses interconnected links from the initial layer to the output layer and determines the normal and abnormal behavior patterns and produces a perfect classification. We execute a set of experiments on five popular IIoT datasets: gas pipeline, water storage tank, NSLKDD+, UNSW-NB15, and X-IIoTID. We compare PIGNUS to the state-of-the-art models in terms of accuracy, False Positive Ratio (FPR), precision, and recall. The results show that PIGNUS provides more than 95% accuracy, which is 25% better on average than the existing models. In the other parameters, PIGNUS shows 20% improved FPR, 10% better recall, and 10% better in precision. Overall, PIGNUS proves its efficiency as an IDS solution for IIoTs. Thus, PIGNUS is an efficient solution for IIoTs.
published_date 2023-09-30T15:08:07Z
_version_ 1805922690715877376
score 11.035634

Similar Items