Automated CVE Severity Prediction Using Deep Learning and Explainable AI

Automated CVE Severity Prediction Using Deep Learning and Explainable AI | 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 Automated CVE Severity Prediction Using Deep Learning and Explainable AI Omar Yasin, Qasem Abu Al-Haija, Yousef AbuHour This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7123186/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Cybersecurity vulnerabilities represent a critical threat to information systems, often leading to data breaches and operational disruptions. Accurate assessment of vulnerability severity is therefore essential for effective risk prioritization. The Common Vulnerabilities and Exposures (CVE) system maintains a catalog of such vulnerabilities, each accompanied by a brief textual description and a severity score, typically assigned using the Common Vulnerability Scoring System (CVSS). However, assigning severity scores is time-consuming and resource-intensive, underscoring the need for automated prediction methods. In this study, we explore the automatic prediction of CVE severity levels directly from textual descriptions using machine learning. To address class imbalance, we leverage GPT-Neo, a generative language model, to synthetically augment underrepresented categories. We fine-tune a DeBERTa-based deep learning model for classification, achieving high accuracy in predicting severity levels from text alone. To enhance the interpretability of our model, we employ Local Interpretable Model-agnostic Explanations (LIME) to identify key terms and phrases that most strongly influenced model decisions. This approach demonstrates strong predictive performance and provides insight into the linguistic patterns associated with vulnerability severity. Theoretical Computer Science Artificial Intelligence and Machine Learning Cybersecurity Vulnerabilities CVE Severity Prediction Machine Learning Classification Data Augmentation Model Interpretability (LIME) Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted 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-7123186","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":485296278,"identity":"705fcab1-0caf-40cf-baf1-ef1fe557c1e6","order_by":0,"name":"Omar Yasin","email":"","orcid":"","institution":"Princess Sumaya University for Technology","correspondingAuthor":false,"prefix":"","firstName":"Omar","middleName":"","lastName":"Yasin","suffix":""},{"id":485296279,"identity":"2034f6e3-78b6-40a1-85a2-30f17012404c","order_by":1,"name":"Qasem Abu Al-Haija","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABA0lEQVRIiWNgGAWjYHACNgbGBgYexgbmAwYQgQQGBgnitLAlALUYEK8FCHhAyqFa8AG+84efPebdYSfD3H7mQzHPnz8M/Ow5BgwWFbi1SN5IMzfmPZPMw9iTu8GYt82AQbLnjQGDxBncWgxuMJhJ87YxA/0C0tJgABQB2iLZhkfL+ePfgFrqeRj73zww5vljwGBPUMuBHJAth3kYZ+QwGPOwAW2RIKBF8kZOueHctuNALc8MgAxjHokzzwoO4PML3/nj2x68bau2N+xPfmbw5o+cHH978sbHEnhCjOEAlDZsYGADRQoPiHMYb1TCtMgzMDA/gAkyfsCnZRSMglEwCkYaAABn8U097Oxo0QAAAABJRU5ErkJggg==","orcid":"","institution":"Jordan University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Qasem","middleName":"Abu","lastName":"Al-Haija","suffix":""},{"id":485296280,"identity":"d855fa0b-7752-472a-afb7-95925acdfc09","order_by":2,"name":"Yousef AbuHour","email":"","orcid":"","institution":"Princess Sumaya University for Technology","correspondingAuthor":false,"prefix":"","firstName":"Yousef","middleName":"","lastName":"AbuHour","suffix":""}],"badges":[],"createdAt":"2025-07-14 16:26:51","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-7123186/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7123186/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":86759467,"identity":"ac51a4ae-727f-44e8-a042-bea930c8225b","added_by":"auto","created_at":"2025-07-15 10:04:22","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":495866,"visible":true,"origin":"","legend":"","description":"","filename":"AnalyzingCybersecurityThreatswithCVESeverityPrediction1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7123186/v1_covered_42fc67e8-3ac1-4e9a-b032-0c71d0e5689e.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eAutomated CVE Severity Prediction Using Deep Learning and Explainable AI\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Princess Sumaya University for Technology","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Cybersecurity Vulnerabilities, CVE Severity Prediction, Machine Learning Classification, Data Augmentation, Model Interpretability (LIME)","lastPublishedDoi":"10.21203/rs.3.rs-7123186/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7123186/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eCybersecurity vulnerabilities represent a critical threat to information systems, often leading to data breaches and operational disruptions. Accurate assessment of vulnerability severity is therefore essential for effective risk prioritization. The Common Vulnerabilities and Exposures (CVE) system maintains a catalog of such vulnerabilities, each accompanied by a brief textual description and a severity score, typically assigned using the Common Vulnerability Scoring System (CVSS). However, assigning severity scores is time-consuming and resource-intensive, underscoring the need for automated prediction methods. In this study, we explore the automatic prediction of CVE severity levels directly from textual descriptions using machine learning. To address class imbalance, we leverage GPT-Neo, a generative language model, to synthetically augment underrepresented categories. We fine-tune a DeBERTa-based deep learning model for classification, achieving high accuracy in predicting severity levels from text alone. To enhance the interpretability of our model, we employ Local Interpretable Model-agnostic Explanations (LIME) to identify key terms and phrases that most strongly influenced model decisions. This approach demonstrates strong predictive performance and provides insight into the linguistic patterns associated with vulnerability severity.\u003c/p\u003e","manuscriptTitle":"Automated CVE Severity Prediction Using Deep Learning and Explainable AI","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-15 09:56:15","doi":"10.21203/rs.3.rs-7123186/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"97d9b042-92e7-4dda-bb99-3da4a075edda","owner":[],"postedDate":"July 15th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":51555514,"name":"Theoretical Computer Science"},{"id":51555515,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-07-15T09:56:15+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-15 09:56:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7123186","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7123186","identity":"rs-7123186","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}