Machine Learning-Enabled IoT Security: Open Issues and Challenges Under Advanced Persistent Threats

Despite its technological benefits, the Internet of Things (IoT) has cyber weaknesses due to vulnerabilities in the wireless medium. Machine Larning (ML)-based methods are widely used against cyber threats in IoT networks with promising performance. An Advanced Persistent Threat (APT) is prominent f...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:ACM computing surveys 2022-12, Vol.55 (5), p.1-37, Article 105
Hauptverfasser: Chen, Zhiyan, Liu, Jinxin, Shen, Yu, Simsek, Murat, Kantarci, Burak, Mouftah, Hussein T., Djukic, Petar
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 37
container_issue 5
container_start_page 1
container_title ACM computing surveys
container_volume 55
creator Chen, Zhiyan
Liu, Jinxin
Shen, Yu
Simsek, Murat
Kantarci, Burak
Mouftah, Hussein T.
Djukic, Petar
description Despite its technological benefits, the Internet of Things (IoT) has cyber weaknesses due to vulnerabilities in the wireless medium. Machine Larning (ML)-based methods are widely used against cyber threats in IoT networks with promising performance. An Advanced Persistent Threat (APT) is prominent for cybercriminals to compromise networks, and it is crucial to long-term and harmful characteristics. However, it is difficult to apply ML-based approaches to identify APT attacks to obtain a promising detection performance due to an extremely small percentage among normal traffic. There are limited surveys that fully investigate APT attacks in IoT networks due to the lack of public datasets with all types of APT attacks. It is worth bridging the state of the art in network attack detection with APT attack detection in a comprehensive review article. This survey article reviews the security challenges in IoT networks and presents well-known attacks, APT attacks, and threat models in IoT systems. Meanwhile, signature-based, anomaly-based, and hybrid intrusion detection systems are summarized for IoT networks. The article highlights statistical insights regarding frequently applied ML-based methods against network intrusion. Finally, open issues and challenges for common network intrusion and APT attacks are presented for future research.
doi_str_mv 10.1145/3530812
format Article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2817774219</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2817774219</sourcerecordid><originalsourceid>FETCH-LOGICAL-a272t-e8c44d99f8b7e7452c52f754d6e6413969a6d4b4fb7d19259d22adb4cc5cf8bf3</originalsourceid><addsrcrecordid>eNo9kM1LAzEQxYMoWKt49xTw4Gk1n5uNt1KqFioVbM9LNpltt2yzNdkK_e-NtHoahvm994aH0C0lj5QK-cQlJwVlZ2hApVSZ4oKeowHhOckIJ-QSXcW4IYQwQfMBsu_GrhsPeAYm-Mavsok3VQsOT7sF_gS7D01_eMbzHXg8jXEPERvv8Hht2hb8Kq1L7yDgkfs23ibdB4TYxB58jxfrAKaP1-iiNm2Em9McouXLZDF-y2bz1-l4NMsMU6zPoLBCOK3rolKghGRWslpJ4XLIBeU61yZ3ohJ1pRzVTGrHmHGVsFbapKn5EN0ffXeh-0qP9uWm2wefIktWUKWUYFQn6uFI2dDFGKAud6HZmnAoKSl_GyxPDSby7kgau_2H_o4_oq9qgQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2817774219</pqid></control><display><type>article</type><title>Machine Learning-Enabled IoT Security: Open Issues and Challenges Under Advanced Persistent Threats</title><source>ACM Digital Library</source><creator>Chen, Zhiyan ; Liu, Jinxin ; Shen, Yu ; Simsek, Murat ; Kantarci, Burak ; Mouftah, Hussein T. ; Djukic, Petar</creator><creatorcontrib>Chen, Zhiyan ; Liu, Jinxin ; Shen, Yu ; Simsek, Murat ; Kantarci, Burak ; Mouftah, Hussein T. ; Djukic, Petar</creatorcontrib><description>Despite its technological benefits, the Internet of Things (IoT) has cyber weaknesses due to vulnerabilities in the wireless medium. Machine Larning (ML)-based methods are widely used against cyber threats in IoT networks with promising performance. An Advanced Persistent Threat (APT) is prominent for cybercriminals to compromise networks, and it is crucial to long-term and harmful characteristics. However, it is difficult to apply ML-based approaches to identify APT attacks to obtain a promising detection performance due to an extremely small percentage among normal traffic. There are limited surveys that fully investigate APT attacks in IoT networks due to the lack of public datasets with all types of APT attacks. It is worth bridging the state of the art in network attack detection with APT attack detection in a comprehensive review article. This survey article reviews the security challenges in IoT networks and presents well-known attacks, APT attacks, and threat models in IoT systems. Meanwhile, signature-based, anomaly-based, and hybrid intrusion detection systems are summarized for IoT networks. The article highlights statistical insights regarding frequently applied ML-based methods against network intrusion. Finally, open issues and challenges for common network intrusion and APT attacks are presented for future research.</description><identifier>ISSN: 0360-0300</identifier><identifier>EISSN: 1557-7341</identifier><identifier>DOI: 10.1145/3530812</identifier><language>eng</language><publisher>New York, NY: ACM</publisher><subject>Computer science ; Computing methodologies ; Cybersecurity ; Hybrid systems ; Internet of Things ; Intrusion detection systems ; Machine learning ; Network security ; Networks ; Security and privacy ; Sensor networks ; Threat models</subject><ispartof>ACM computing surveys, 2022-12, Vol.55 (5), p.1-37, Article 105</ispartof><rights>Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from</rights><rights>Copyright Association for Computing Machinery May 2023</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-a272t-e8c44d99f8b7e7452c52f754d6e6413969a6d4b4fb7d19259d22adb4cc5cf8bf3</citedby><cites>FETCH-LOGICAL-a272t-e8c44d99f8b7e7452c52f754d6e6413969a6d4b4fb7d19259d22adb4cc5cf8bf3</cites><orcidid>0000-0002-2482-9548 ; 0000-0001-7939-7212 ; 0000-0001-8856-8706 ; 0000-0003-3156-5760 ; 0000-0003-0220-7956 ; 0000-0003-4699-0006 ; 0000-0003-4397-1061</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://dl.acm.org/doi/pdf/10.1145/3530812$$EPDF$$P50$$Gacm$$H</linktopdf><link.rule.ids>314,780,784,2282,27924,27925,40196,76228</link.rule.ids></links><search><creatorcontrib>Chen, Zhiyan</creatorcontrib><creatorcontrib>Liu, Jinxin</creatorcontrib><creatorcontrib>Shen, Yu</creatorcontrib><creatorcontrib>Simsek, Murat</creatorcontrib><creatorcontrib>Kantarci, Burak</creatorcontrib><creatorcontrib>Mouftah, Hussein T.</creatorcontrib><creatorcontrib>Djukic, Petar</creatorcontrib><title>Machine Learning-Enabled IoT Security: Open Issues and Challenges Under Advanced Persistent Threats</title><title>ACM computing surveys</title><addtitle>ACM CSUR</addtitle><description>Despite its technological benefits, the Internet of Things (IoT) has cyber weaknesses due to vulnerabilities in the wireless medium. Machine Larning (ML)-based methods are widely used against cyber threats in IoT networks with promising performance. An Advanced Persistent Threat (APT) is prominent for cybercriminals to compromise networks, and it is crucial to long-term and harmful characteristics. However, it is difficult to apply ML-based approaches to identify APT attacks to obtain a promising detection performance due to an extremely small percentage among normal traffic. There are limited surveys that fully investigate APT attacks in IoT networks due to the lack of public datasets with all types of APT attacks. It is worth bridging the state of the art in network attack detection with APT attack detection in a comprehensive review article. This survey article reviews the security challenges in IoT networks and presents well-known attacks, APT attacks, and threat models in IoT systems. Meanwhile, signature-based, anomaly-based, and hybrid intrusion detection systems are summarized for IoT networks. The article highlights statistical insights regarding frequently applied ML-based methods against network intrusion. Finally, open issues and challenges for common network intrusion and APT attacks are presented for future research.</description><subject>Computer science</subject><subject>Computing methodologies</subject><subject>Cybersecurity</subject><subject>Hybrid systems</subject><subject>Internet of Things</subject><subject>Intrusion detection systems</subject><subject>Machine learning</subject><subject>Network security</subject><subject>Networks</subject><subject>Security and privacy</subject><subject>Sensor networks</subject><subject>Threat models</subject><issn>0360-0300</issn><issn>1557-7341</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNo9kM1LAzEQxYMoWKt49xTw4Gk1n5uNt1KqFioVbM9LNpltt2yzNdkK_e-NtHoahvm994aH0C0lj5QK-cQlJwVlZ2hApVSZ4oKeowHhOckIJ-QSXcW4IYQwQfMBsu_GrhsPeAYm-Mavsok3VQsOT7sF_gS7D01_eMbzHXg8jXEPERvv8Hht2hb8Kq1L7yDgkfs23ibdB4TYxB58jxfrAKaP1-iiNm2Em9McouXLZDF-y2bz1-l4NMsMU6zPoLBCOK3rolKghGRWslpJ4XLIBeU61yZ3ohJ1pRzVTGrHmHGVsFbapKn5EN0ffXeh-0qP9uWm2wefIktWUKWUYFQn6uFI2dDFGKAud6HZmnAoKSl_GyxPDSby7kgau_2H_o4_oq9qgQ</recordid><startdate>20221203</startdate><enddate>20221203</enddate><creator>Chen, Zhiyan</creator><creator>Liu, Jinxin</creator><creator>Shen, Yu</creator><creator>Simsek, Murat</creator><creator>Kantarci, Burak</creator><creator>Mouftah, Hussein T.</creator><creator>Djukic, Petar</creator><general>ACM</general><general>Association for Computing Machinery</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-2482-9548</orcidid><orcidid>https://orcid.org/0000-0001-7939-7212</orcidid><orcidid>https://orcid.org/0000-0001-8856-8706</orcidid><orcidid>https://orcid.org/0000-0003-3156-5760</orcidid><orcidid>https://orcid.org/0000-0003-0220-7956</orcidid><orcidid>https://orcid.org/0000-0003-4699-0006</orcidid><orcidid>https://orcid.org/0000-0003-4397-1061</orcidid></search><sort><creationdate>20221203</creationdate><title>Machine Learning-Enabled IoT Security: Open Issues and Challenges Under Advanced Persistent Threats</title><author>Chen, Zhiyan ; Liu, Jinxin ; Shen, Yu ; Simsek, Murat ; Kantarci, Burak ; Mouftah, Hussein T. ; Djukic, Petar</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a272t-e8c44d99f8b7e7452c52f754d6e6413969a6d4b4fb7d19259d22adb4cc5cf8bf3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer science</topic><topic>Computing methodologies</topic><topic>Cybersecurity</topic><topic>Hybrid systems</topic><topic>Internet of Things</topic><topic>Intrusion detection systems</topic><topic>Machine learning</topic><topic>Network security</topic><topic>Networks</topic><topic>Security and privacy</topic><topic>Sensor networks</topic><topic>Threat models</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Chen, Zhiyan</creatorcontrib><creatorcontrib>Liu, Jinxin</creatorcontrib><creatorcontrib>Shen, Yu</creatorcontrib><creatorcontrib>Simsek, Murat</creatorcontrib><creatorcontrib>Kantarci, Burak</creatorcontrib><creatorcontrib>Mouftah, Hussein T.</creatorcontrib><creatorcontrib>Djukic, Petar</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>ACM computing surveys</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Chen, Zhiyan</au><au>Liu, Jinxin</au><au>Shen, Yu</au><au>Simsek, Murat</au><au>Kantarci, Burak</au><au>Mouftah, Hussein T.</au><au>Djukic, Petar</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Machine Learning-Enabled IoT Security: Open Issues and Challenges Under Advanced Persistent Threats</atitle><jtitle>ACM computing surveys</jtitle><stitle>ACM CSUR</stitle><date>2022-12-03</date><risdate>2022</risdate><volume>55</volume><issue>5</issue><spage>1</spage><epage>37</epage><pages>1-37</pages><artnum>105</artnum><issn>0360-0300</issn><eissn>1557-7341</eissn><abstract>Despite its technological benefits, the Internet of Things (IoT) has cyber weaknesses due to vulnerabilities in the wireless medium. Machine Larning (ML)-based methods are widely used against cyber threats in IoT networks with promising performance. An Advanced Persistent Threat (APT) is prominent for cybercriminals to compromise networks, and it is crucial to long-term and harmful characteristics. However, it is difficult to apply ML-based approaches to identify APT attacks to obtain a promising detection performance due to an extremely small percentage among normal traffic. There are limited surveys that fully investigate APT attacks in IoT networks due to the lack of public datasets with all types of APT attacks. It is worth bridging the state of the art in network attack detection with APT attack detection in a comprehensive review article. This survey article reviews the security challenges in IoT networks and presents well-known attacks, APT attacks, and threat models in IoT systems. Meanwhile, signature-based, anomaly-based, and hybrid intrusion detection systems are summarized for IoT networks. The article highlights statistical insights regarding frequently applied ML-based methods against network intrusion. Finally, open issues and challenges for common network intrusion and APT attacks are presented for future research.</abstract><cop>New York, NY</cop><pub>ACM</pub><doi>10.1145/3530812</doi><tpages>37</tpages><orcidid>https://orcid.org/0000-0002-2482-9548</orcidid><orcidid>https://orcid.org/0000-0001-7939-7212</orcidid><orcidid>https://orcid.org/0000-0001-8856-8706</orcidid><orcidid>https://orcid.org/0000-0003-3156-5760</orcidid><orcidid>https://orcid.org/0000-0003-0220-7956</orcidid><orcidid>https://orcid.org/0000-0003-4699-0006</orcidid><orcidid>https://orcid.org/0000-0003-4397-1061</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 0360-0300
ispartof ACM computing surveys, 2022-12, Vol.55 (5), p.1-37, Article 105
issn 0360-0300
1557-7341
language eng
recordid cdi_proquest_journals_2817774219
source ACM Digital Library
subjects Computer science
Computing methodologies
Cybersecurity
Hybrid systems
Internet of Things
Intrusion detection systems
Machine learning
Network security
Networks
Security and privacy
Sensor networks
Threat models
title Machine Learning-Enabled IoT Security: Open Issues and Challenges Under Advanced Persistent Threats
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-20T23%3A44%3A45IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Machine%20Learning-Enabled%20IoT%20Security:%20Open%20Issues%20and%20Challenges%20Under%20Advanced%20Persistent%20Threats&rft.jtitle=ACM%20computing%20surveys&rft.au=Chen,%20Zhiyan&rft.date=2022-12-03&rft.volume=55&rft.issue=5&rft.spage=1&rft.epage=37&rft.pages=1-37&rft.artnum=105&rft.issn=0360-0300&rft.eissn=1557-7341&rft_id=info:doi/10.1145/3530812&rft_dat=%3Cproquest_cross%3E2817774219%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2817774219&rft_id=info:pmid/&rfr_iscdi=true