Privacy-Preserving Distributed IDS Using Incremental Learning for IoT Health Systems

<p>Existing techniques for incremental learning are computationally expensive and produce duplicate features leading to higher false positive and true negative rates. We propose a novel privacy-preserving intrusion detection pipeline for distributed incremental learning. Our pre-processing tec...

Full description

Saved in:
Bibliographic Details
Main Author: Aliya Tabassum (16896486) (author)
Other Authors: Aiman Erbad (14150589) (author), Amr Mohamed (3508121) (author), Mohsen Guizani (12580291) (author)
Published: 2021
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513560469569536
author Aliya Tabassum (16896486)
author2 Aiman Erbad (14150589)
Amr Mohamed (3508121)
Mohsen Guizani (12580291)
author2_role author
author
author
author_facet Aliya Tabassum (16896486)
Aiman Erbad (14150589)
Amr Mohamed (3508121)
Mohsen Guizani (12580291)
author_role author
dc.creator.none.fl_str_mv Aliya Tabassum (16896486)
Aiman Erbad (14150589)
Amr Mohamed (3508121)
Mohsen Guizani (12580291)
dc.date.none.fl_str_mv 2021-01-13T00:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2021.3051530
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Privacy-Preserving_Distributed_IDS_Using_Incremental_Learning_for_IoT_Health_Systems/24049365
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Biomedical engineering
Information and computing sciences
Cybersecurity and privacy
Distributed computing and systems software
Machine learning
Feature extraction
Deep learning
Security
Real-time systems
Intrusion detection
Data models
Task analysis
Internet of things (IoT)
Intrusion detection system (IDS)
Incremental learning
Pre-processing
dc.title.none.fl_str_mv Privacy-Preserving Distributed IDS Using Incremental Learning for IoT Health Systems
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>Existing techniques for incremental learning are computationally expensive and produce duplicate features leading to higher false positive and true negative rates. We propose a novel privacy-preserving intrusion detection pipeline for distributed incremental learning. Our pre-processing technique eliminates redundancies and selects unique features by following innovative extraction techniques. We use autoencoders with non-negativity constraints, which help us extract less redundant features. More importantly, the distributed intrusion detection model reduces the burden on the edge classifier and distributes the load among IoT and edge devices. Theoretical analysis and numerical experiments have shown lower space and time costs than state of the art techniques, with comparable classification accuracy. Extensive experiments with standard data sets and real-time streaming IoT traffic give encouraging results.</p><h2>Other Information</h2><p>Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2021.3051530" target="_blank">https://dx.doi.org/10.1109/access.2021.3051530</a></p>
eu_rights_str_mv openAccess
id Manara2_7bf03fa2c50b91aee44600539eefdf8c
identifier_str_mv 10.1109/access.2021.3051530
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24049365
publishDate 2021
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Privacy-Preserving Distributed IDS Using Incremental Learning for IoT Health SystemsAliya Tabassum (16896486)Aiman Erbad (14150589)Amr Mohamed (3508121)Mohsen Guizani (12580291)EngineeringBiomedical engineeringInformation and computing sciencesCybersecurity and privacyDistributed computing and systems softwareMachine learningFeature extractionDeep learningSecurityReal-time systemsIntrusion detectionData modelsTask analysisInternet of things (IoT)Intrusion detection system (IDS)Incremental learningPre-processing<p>Existing techniques for incremental learning are computationally expensive and produce duplicate features leading to higher false positive and true negative rates. We propose a novel privacy-preserving intrusion detection pipeline for distributed incremental learning. Our pre-processing technique eliminates redundancies and selects unique features by following innovative extraction techniques. We use autoencoders with non-negativity constraints, which help us extract less redundant features. More importantly, the distributed intrusion detection model reduces the burden on the edge classifier and distributes the load among IoT and edge devices. Theoretical analysis and numerical experiments have shown lower space and time costs than state of the art techniques, with comparable classification accuracy. Extensive experiments with standard data sets and real-time streaming IoT traffic give encouraging results.</p><h2>Other Information</h2><p>Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2021.3051530" target="_blank">https://dx.doi.org/10.1109/access.2021.3051530</a></p>2021-01-13T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2021.3051530https://figshare.com/articles/journal_contribution/Privacy-Preserving_Distributed_IDS_Using_Incremental_Learning_for_IoT_Health_Systems/24049365CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/240493652021-01-13T00:00:00Z
spellingShingle Privacy-Preserving Distributed IDS Using Incremental Learning for IoT Health Systems
Aliya Tabassum (16896486)
Engineering
Biomedical engineering
Information and computing sciences
Cybersecurity and privacy
Distributed computing and systems software
Machine learning
Feature extraction
Deep learning
Security
Real-time systems
Intrusion detection
Data models
Task analysis
Internet of things (IoT)
Intrusion detection system (IDS)
Incremental learning
Pre-processing
status_str publishedVersion
title Privacy-Preserving Distributed IDS Using Incremental Learning for IoT Health Systems
title_full Privacy-Preserving Distributed IDS Using Incremental Learning for IoT Health Systems
title_fullStr Privacy-Preserving Distributed IDS Using Incremental Learning for IoT Health Systems
title_full_unstemmed Privacy-Preserving Distributed IDS Using Incremental Learning for IoT Health Systems
title_short Privacy-Preserving Distributed IDS Using Incremental Learning for IoT Health Systems
title_sort Privacy-Preserving Distributed IDS Using Incremental Learning for IoT Health Systems
topic Engineering
Biomedical engineering
Information and computing sciences
Cybersecurity and privacy
Distributed computing and systems software
Machine learning
Feature extraction
Deep learning
Security
Real-time systems
Intrusion detection
Data models
Task analysis
Internet of things (IoT)
Intrusion detection system (IDS)
Incremental learning
Pre-processing