An Explainable Machine Learning-Based Approach for Pre-Deployment Security Analysis of Docker Images

An Explainable Machine Learning-Based Approach for Pre-Deployment Security Analysis of Docker Images | 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 An Explainable Machine Learning-Based Approach for Pre-Deployment Security Analysis of Docker Images Hirushi Fernando, Lakshan Costa This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9488487/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 12 You are reading this latest preprint version Abstract Containerization technologies, particularly Docker,have become essential in modern cloud-native application deployment. However, Docker images sourced from public andprivate registries may contain hidden vulnerabilities, insecureconfigurations, and malicious components, posing significantsecurity risks. Traditional security tools rely mainly on rule-basedvulnerability detection and known CVE databases, limiting theirability to identify zero-day and unknown threats. This paper proposes a machine learning-based framework forproactive security assessment of Docker images before deployment. The system extracts key structural and configuration features from container images and applies XGBoost regression forvulnerability scoring, XGBoost classification for secure/insecuredetection, and Isolation Forest for anomaly detection. The proposed approach enables early identification of risky images withinCI/CD pipelines. Experimental results indicate that machine learning-basedmethods improve detection capability compared to traditionalvulnerability scanning approaches, enhancing overall containersecurity in cloud environments. Docker security container security machine learning vulnerability detection cloud security Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 11 May, 2026 Reviews received at journal 10 May, 2026 Reviewers agreed at journal 05 May, 2026 Reviews received at journal 30 Apr, 2026 Reviewers agreed at journal 30 Apr, 2026 Reviewers agreed at journal 30 Apr, 2026 Reviewers agreed at journal 30 Apr, 2026 Reviewers agreed at journal 30 Apr, 2026 Reviewers invited by journal 30 Apr, 2026 Editor assigned by journal 28 Apr, 2026 Submission checks completed at journal 27 Apr, 2026 First submitted to journal 21 Apr, 2026 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-9488487","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":634703577,"identity":"582460df-2c5b-4e46-9a0b-99af13804216","order_by":0,"name":"Hirushi Fernando","email":"data:image/png;base64,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","orcid":"","institution":"Informatics Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Hirushi","middleName":"","lastName":"Fernando","suffix":""},{"id":634703578,"identity":"a566eb8a-f389-4bc0-968b-c1fe501a8553","order_by":1,"name":"Lakshan Costa","email":"","orcid":"","institution":"Informatics Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Lakshan","middleName":"","lastName":"Costa","suffix":""}],"badges":[],"createdAt":"2026-04-21 20:38:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9488487/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9488487/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108807072,"identity":"31db5072-1aa6-4ee5-b254-8ce0fc888a77","added_by":"auto","created_at":"2026-05-08 15:30:04","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2454251,"visible":true,"origin":"","legend":"","description":"","filename":"FullResearchPaper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9488487/v1_covered_1d55b779-4828-4891-87ff-7db60b7daf7f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"An Explainable Machine Learning-Based Approach for Pre-Deployment Security Analysis of Docker Images","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"journal-of-cloud-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"clco","sideBox":"Learn more about [Journal of Cloud Computing](http://journalofcloudcomputing.springeropen.com)","snPcode":"13677","submissionUrl":"https://submission.nature.com/new-submission/13677/3","title":"Journal of Cloud Computing","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Docker security, container security, machine learning, vulnerability detection, cloud security","lastPublishedDoi":"10.21203/rs.3.rs-9488487/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9488487/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eContainerization technologies, particularly Docker,have become essential in modern cloud-native application deployment. However, Docker images sourced from public andprivate registries may contain hidden vulnerabilities, insecureconfigurations, and malicious components, posing significantsecurity risks. Traditional security tools rely mainly on rule-basedvulnerability detection and known CVE databases, limiting theirability to identify zero-day and unknown threats.\u003c/p\u003e\n\u003cp\u003eThis paper proposes a machine learning-based framework forproactive security assessment of Docker images before deployment. The system extracts key structural and configuration features from container images and applies XGBoost regression forvulnerability scoring, XGBoost classification for secure/insecuredetection, and Isolation Forest for anomaly detection. The proposed approach enables early identification of risky images withinCI/CD pipelines.\u003c/p\u003e\n\u003cp\u003eExperimental results indicate that machine learning-basedmethods improve detection capability compared to traditionalvulnerability scanning approaches, enhancing overall containersecurity in cloud environments.\u003c/p\u003e","manuscriptTitle":"An Explainable Machine Learning-Based Approach for Pre-Deployment Security Analysis of Docker Images","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-08 04:07:27","doi":"10.21203/rs.3.rs-9488487/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-12T03:17:39+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-10T12:05:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"318513858361543781830207853583479549087","date":"2026-05-05T09:47:21+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-30T16:00:46+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"290477856968775832909641024590815809985","date":"2026-04-30T13:26:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"338667583577164407672057103240641752242","date":"2026-04-30T05:28:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"62313520836180695864673307726763893925","date":"2026-04-30T04:58:13+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"189813722084674487723259620027284823221","date":"2026-04-30T04:53:39+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-30T04:47:34+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-28T05:28:57+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-27T14:22:58+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Cloud Computing","date":"2026-04-21T20:22:30+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-cloud-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"clco","sideBox":"Learn more about [Journal of Cloud Computing](http://journalofcloudcomputing.springeropen.com)","snPcode":"13677","submissionUrl":"https://submission.nature.com/new-submission/13677/3","title":"Journal of Cloud Computing","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"1c9fdc47-b7ae-4b24-b2ae-657d2e769f4c","owner":[],"postedDate":"May 8th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-12T03:17:39+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-10T12:05:33+00:00","index":47,"fulltext":""},{"type":"reviewerAgreed","content":"318513858361543781830207853583479549087","date":"2026-05-05T09:47:21+00:00","index":46,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-30T16:00:46+00:00","index":43,"fulltext":""},{"type":"reviewerAgreed","content":"290477856968775832909641024590815809985","date":"2026-04-30T13:26:55+00:00","index":42,"fulltext":""},{"type":"reviewerAgreed","content":"338667583577164407672057103240641752242","date":"2026-04-30T05:28:34+00:00","index":40,"fulltext":""},{"type":"reviewerAgreed","content":"62313520836180695864673307726763893925","date":"2026-04-30T04:58:13+00:00","index":39,"fulltext":""},{"type":"reviewerAgreed","content":"189813722084674487723259620027284823221","date":"2026-04-30T04:53:39+00:00","index":38,"fulltext":""},{"type":"reviewersInvited","content":"27","date":"2026-04-30T04:47:34+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-05-12T03:26:45+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-08 04:07:27","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9488487","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9488487","identity":"rs-9488487","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}