Atomic-Inspired Hybrid Feature Model for Robust Android Malware Detection

Atomic-Inspired Hybrid Feature Model for Robust Android Malware Detection | 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 Atomic-Inspired Hybrid Feature Model for Robust Android Malware Detection Mohd Fozla Rabby This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7485799/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 We created a hybrid feature framework for finding Android malware that combines static and dynamic analysis methods. Static features are taken from APK metadata and DEX bytecode images, while dynamic behaviors are recorded using sequences of runtime API calls. The combination of the different features has given us a better picture of how Android apps work. We have added an atomic-inspired design of features to the framework for modeling both the structural and behavioral traits of applications. This is helping to find malware more easily. All application samples come from the AndroZoo repository, which is open to the public. A machine learning pipeline is used, and it is combined with image-based CNN embeddings structured features to use an XGBoost classifier to tell the difference between good and bad apps. Our experimental findings indicate a precision of 99.93%, highlighting the resilience of the proposed hybrid detection methodology. Android Malware Hybrid Dataset Machine Learning Malware Detection Static Analysis Dynamic Analysis Full Text Additional Declarations No competing interests reported. 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-7485799","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":507751704,"identity":"7f5011bf-7283-4533-ac66-2b84d810cff7","order_by":0,"name":"Mohd Fozla Rabby","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7UlEQVRIie2RsYrCQBCGxxPWZiDtSCS+giHgCb5M0phGra0kNqbxAZTzYQILsVn72AlpVQI2FiKOVlftaie4X7W7zMf8MwtgsXwkKAAmhO1Gwpfs+SQAjYrqef4ie0epzScBFOGLym+6zUsUFM1WZVlVSoKTZmJ/0CgtNY4DRIpSd9BtLgsJpMKGv9YoBMOui8Rd/oaijpUEKEC4umDkHFjpUJTsVP18ZaVtVOjRJSQeH8EFDtYxK6fYX2fES+ZZFipGX0WpfhZnlO+Ptyl/pSyrS973vI3MtRt78PM/Bp9riUHgkouxxGKxWL6aO2rzSxn5QAYQAAAAAElFTkSuQmCC","orcid":"","institution":"Khulna University","correspondingAuthor":true,"prefix":"","firstName":"Mohd","middleName":"Fozla","lastName":"Rabby","suffix":""}],"badges":[],"createdAt":"2025-08-29 07:08:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7485799/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7485799/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102863472,"identity":"d0052698-b73c-4e8c-899d-2ee46ae796d3","added_by":"auto","created_at":"2026-02-17 16:26:21","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":657583,"visible":true,"origin":"","legend":"","description":"","filename":"manuscriptrev.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7485799/v1_covered_c1ab0aa6-45d6-43a7-92bb-2ac2486ae155.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Atomic-Inspired Hybrid Feature Model for Robust Android Malware Detection","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"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":"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":"Android Malware, Hybrid Dataset, Machine Learning, Malware Detection, Static Analysis, Dynamic Analysis","lastPublishedDoi":"10.21203/rs.3.rs-7485799/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7485799/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"We created a hybrid feature framework for finding Android malware that combines static and dynamic analysis methods. Static features are taken from APK metadata and DEX bytecode images, while dynamic behaviors are recorded using sequences of runtime API calls. The combination of the different features has given us a better picture of how Android apps work. We have added an atomic-inspired design of features to the framework for modeling both the structural and behavioral traits of applications. This is helping to find malware more easily. All application samples come from the AndroZoo repository, which is open to the public. A machine learning pipeline is used, and it is combined with image-based CNN embeddings structured features to use an XGBoost classifier to tell the difference between good and bad apps. Our experimental findings indicate a precision of 99.93\\%, highlighting the resilience of the proposed hybrid detection methodology.","manuscriptTitle":"Atomic-Inspired Hybrid Feature Model for Robust Android Malware Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-01 03:32:46","doi":"10.21203/rs.3.rs-7485799/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":"414c683c-59c6-4b2e-847e-e866da927938","owner":[],"postedDate":"September 1st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-02-17T16:26:05+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-01 03:32:46","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7485799","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7485799","identity":"rs-7485799","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}