Semi-supervised Attack Detection in Industrial Control Systems with Deviation Networks and Feature Selection

Semi-supervised Attack Detection in Industrial Control Systems with Deviation Networks and Feature Selection | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Semi-supervised Attack Detection in Industrial Control Systems with Deviation Networks and Feature Selection Yanhua Liu, Wentao Deng, Zhihuang Liu, Fanhao Zeng This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3101948/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 21 Mar, 2024 Read the published version in The Journal of Supercomputing → Version 1 posted 8 You are reading this latest preprint version Abstract With the rapid development of Industry 4.0, the importance of cyber security for industrial control systems has become increasingly prominent. The complexity and diversity of industrial control systems result in data with high dimensionality and strong correlation, posing significant challenges in obtaining labeled data. However, current intrusion detection methods often demand large amounts of labeled data for effective training. To address this limitation, this paper proposes a semi-supervised anomaly detection framework, called SFSD, which leverages feature selection and deviation networks to detect anomalies in industrial control systems. Specifically, we introduce a feature selection algorithm (IG-PCA) that utilizes information gain and principal component analysis to reduce the dimensionality of features in industrial control data by eliminating redundant features. Then, we propose a semi-supervised learning method based on an improved deviation network, which utilizes an anomaly scoring network to learn end-to-end anomaly scores for the training data, thus assigning anomaly scores to each training data. Finally, using a limited amount of anomaly-labeled data, we design a specific deviation loss function to optimize the anomaly scoring network, enabling a significant score bias between positive and negative samples. Experimental results demonstrate that the proposed SFSD outperforms existing semi-supervised anomaly detection frameworks by improving the accuracy and detection rate by an average of 1-2%. Moreover, SFSD requires less training time compared to existing frameworks, resulting in a training time reduction of approximately 10% or more. Industrial control systems Intrusion detection Feature selection Semi-supervised learning PCA Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 21 Mar, 2024 Read the published version in The Journal of Supercomputing → Version 1 posted Editorial decision: Revision requested 03 Feb, 2024 Reviews received at journal 08 Jan, 2024 Reviewers agreed at journal 07 Jan, 2024 Reviewers agreed at journal 07 Jan, 2024 Reviewers invited by journal 07 Jan, 2024 Editor assigned by journal 28 Jun, 2023 Submission checks completed at journal 28 Jun, 2023 First submitted to journal 23 Jun, 2023 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-3101948","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":214050896,"identity":"7da64c63-f421-43d2-bc3f-902eaa41ca93","order_by":0,"name":"Yanhua Liu","email":"","orcid":"","institution":"Fuzhou University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Yanhua","middleName":"","lastName":"Liu","suffix":""},{"id":214050897,"identity":"ec158bde-d47d-402a-bb67-9497cbb01ead","order_by":1,"name":"Wentao Deng","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0UlEQVRIiWNgGAWjYHACxgcfDCR47NsbGx98IEY9DwMDs+GMAhs5A57DzYYziNTCJs3zIc3YQCK9TZqDGC327IePSfMYHE7cLvmwQZqBwU5Ot4GQLTxpyZZzgFp2zk5sMC5gSDY2O0DQYTmGN94AtTTcTmxInsFwIHEbQS38b4DBBdJy82DDYR6itEjkGEnyGAC9f4OxsZk4LTeeJRvOMLCRk+xJbGacYUCEX9j7kw8++PBHgoef/fjzHx8q7OQIakEDBqQpHwWjYBSMglGAAwAAZx5FHhB9XpUAAAAASUVORK5CYII=","orcid":"","institution":"Fuzhou University","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Wentao","middleName":"","lastName":"Deng","suffix":""},{"id":214050898,"identity":"1a63e427-b41c-4ee6-bcbd-2730c133e44c","order_by":2,"name":"Zhihuang Liu","email":"","orcid":"","institution":"Fuzhou University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Zhihuang","middleName":"","lastName":"Liu","suffix":""},{"id":214050900,"identity":"07ed97ec-8a26-4e3f-948b-e46e7843f665","order_by":3,"name":"Fanhao Zeng","email":"","orcid":"","institution":"Fuzhou University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Fanhao","middleName":"","lastName":"Zeng","suffix":""}],"badges":[],"createdAt":"2023-06-23 21:29:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3101948/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3101948/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11227-024-06018-8","type":"published","date":"2024-03-21T11:08:12+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":58044149,"identity":"ba604e43-4ba8-4076-acbb-0fad6229e70d","added_by":"auto","created_at":"2024-06-10 11:08:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1151708,"visible":true,"origin":"","legend":"","description":"","filename":"SFSDv2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3101948/v1_covered_094bfebd-5165-4bac-a3ef-f09350733e47.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Semi-supervised Attack Detection in Industrial Control Systems with Deviation Networks and Feature Selection","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"the-journal-of-supercomputing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)","snPcode":"11227","submissionUrl":"https://submission.nature.com/new-submission/11227/3","title":"The Journal of Supercomputing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Industrial control systems, Intrusion detection, Feature selection, Semi-supervised learning, PCA","lastPublishedDoi":"10.21203/rs.3.rs-3101948/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3101948/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"With the rapid development of Industry 4.0, the importance of cyber security for industrial control systems has become increasingly prominent. The complexity and diversity of industrial control systems result in data with high dimensionality and strong correlation, posing significant challenges in obtaining labeled data. However, current intrusion detection methods often demand large amounts of labeled data for effective training. To address this limitation, this paper proposes a semi-supervised anomaly detection framework, called SFSD, which leverages feature selection and deviation networks to detect anomalies in industrial control systems. Specifically, we introduce a feature selection algorithm (IG-PCA) that utilizes information gain and principal component analysis to reduce the dimensionality of features in industrial control data by eliminating redundant features. Then, we propose a semi-supervised learning method based on an improved deviation network, which utilizes an anomaly scoring network to learn end-to-end anomaly scores for the training data, thus assigning anomaly scores to each training data. Finally, using a limited amount of anomaly-labeled data, we design a specific deviation loss function to optimize the anomaly scoring network, enabling a significant score bias between positive and negative samples. Experimental results demonstrate that the proposed SFSD outperforms existing semi-supervised anomaly detection frameworks by improving the accuracy and detection rate by an average of 1-2\\%. Moreover, SFSD requires less training time compared to existing frameworks, resulting in a training time reduction of approximately 10\\% or more.","manuscriptTitle":"Semi-supervised Attack Detection in Industrial Control Systems with Deviation Networks and Feature Selection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-07-03 11:19:24","doi":"10.21203/rs.3.rs-3101948/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-02-03T16:29:15+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-01-08T06:04:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"6f58fe45-240d-45a9-b90d-3a45492a7001","date":"2024-01-08T02:21:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"a9f850eb-99cb-4d78-a916-3398d63f633a","date":"2024-01-08T01:23:31+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-01-08T01:14:13+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2023-06-28T14:50:04+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2023-06-28T14:50:03+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Journal of Supercomputing","date":"2023-06-23T21:19:33+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-journal-of-supercomputing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [The Journal of Supercomputing](https://www.springer.com/journal/11227)","snPcode":"11227","submissionUrl":"https://submission.nature.com/new-submission/11227/3","title":"The Journal of Supercomputing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"03c9a5e5-fbb1-4055-bed8-2eee420d7c90","owner":[],"postedDate":"July 3rd, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-06-10T11:08:12+00:00","versionOfRecord":{"articleIdentity":"rs-3101948","link":"https://doi.org/10.1007/s11227-024-06018-8","journal":{"identity":"the-journal-of-supercomputing","isVorOnly":false,"title":"The Journal of Supercomputing"},"publishedOn":"2024-03-21 11:08:12","publishedOnDateReadable":"March 21st, 2024"},"versionCreatedAt":"2023-07-03 11:19:24","video":"","vorDoi":"10.1007/s11227-024-06018-8","vorDoiUrl":"https://doi.org/10.1007/s11227-024-06018-8","workflowStages":[]},"version":"v1","identity":"rs-3101948","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3101948","identity":"rs-3101948","version":["v1"]},"buildId":"7rjqhiLT3MXkJMwkYKINL","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}