Enhancing Data Privacy and Governance in Cloud-Deployed Large Language Models Using Deep Learning-Based Risk Mitigation

Enhancing Data Privacy and Governance in Cloud-Deployed Large Language Models Using Deep Learning-Based Risk Mitigation | 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 Enhancing Data Privacy and Governance in Cloud-Deployed Large Language Models Using Deep Learning-Based Risk Mitigation Naresh Alapati, Ramachander Rao Thallada, Koteswararao Nallabothu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9420186/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 The growing number of problems related to the privacy and security of data in cloud computing requires the need for efficient protection schemes. In this paper, we present an innovative solution for ensuring the privacy and management of data in large language models deployed in clouds by applying risk mitigation techniques based on deep learning. The technique involves risk mitigation, secure data management, and model performance enhancement. First, data input is acquired from a synthesized cybersecurity logs dataset and filtered using data preprocessing to eliminate any form of inconsistencies. Next, data preprocessing enables the input to be directed to the feature extraction phase utilizing the Dense Channel Spatial Semantic Guidance Attention UNet (DCSGA-UNet), which allows for the extraction of relevant features, such as Log_ID, IP_Address, Request_Type, and Response_Time_ms. After that, these features undergo processing through a Bayesian Constitutive Artificial Neural Network (BCANN) classifier that helps predict the probability of a threat or non-threat occurrence. The technique is designed using Python and evaluated against current methods. The experiments show that our innovative solution exhibits a higher accuracy of 98% in a lesser amount of time of 1.07 seconds. Risk Mitigation Clouds Dense Channel Spatial Semantic Guidance Attention Log ID Protection 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-9420186","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":623249291,"identity":"ffd81267-5fab-4c15-960f-477e5146a995","order_by":0,"name":"Naresh Alapati","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2klEQVRIiWNgGAWjYDADAwbmA0BKQoYULWwJIC08pGjhMQDRhLWYs599+Ligxk7eXCLn86sbNRY8DOyHj27Ap8WyJ93YeMaxZMOdM3K3WeccAzqMJy3tBl73HEhjk+ZtYE4wuJG7zTiHDahFgscMv5bzz9h/8zbUA7XkPDPO+UeMlhtpbMy8DYdBWpgf57YRpeUZszTPseOGG848M2PO7ZPgYSPol/NpjJ95aqrlDY4nP/6c861Ojp/98DG8WhBAIIFNAkSzEaccBPgPMH8gXvUoGAWjYBSMJAAAN5FEzUV/ndAAAAAASUVORK5CYII=","orcid":"https://orcid.org/0009-0002-4289-9125","institution":"Walmart","correspondingAuthor":true,"prefix":"","firstName":"Naresh","middleName":"","lastName":"Alapati","suffix":""},{"id":623249292,"identity":"7842b64f-53a7-4a24-be47-4616b91d39c1","order_by":1,"name":"Ramachander Rao Thallada","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA30lEQVRIiWNgGAWjYBAC+xsMjAceMDADmcwHgISEDEEtbBIMDAcSwFrYEkBaeEjRwmMAEiBCi3TzgwMJNdby/O1nPr+6UWPBw8B++OgGvFpkjhkcSDiWbjjjTO4265xjQIfxpKXdwO+wBKAWtsOMGxhytxnnsAG1SPCYEdCS/uFAwr/D9hv43zwzzvlHlJYcgwOJbYcTN0jkMD/ObSNOS8GBxL705Bk3npkx5/ZJ8LAR9kv6xgcfvlnb9vcnP/6c861Ojp/98DG8WlC1g0lilYMA8wdSVI+CUTAKRsHIAQD6rEmKnFWvIQAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0009-0006-8314-2945","institution":"Manulife","correspondingAuthor":true,"prefix":"","firstName":"Ramachander","middleName":"Rao","lastName":"Thallada","suffix":""},{"id":623249293,"identity":"51642f25-7fd1-4014-82c5-aacd3d9a25ce","order_by":2,"name":"Koteswararao Nallabothu","email":"data:image/png;base64,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","orcid":"","institution":"Lowes","correspondingAuthor":true,"prefix":"","firstName":"Koteswararao","middleName":"","lastName":"Nallabothu","suffix":""}],"badges":[],"createdAt":"2026-04-15 00:46:06","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-9420186/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9420186/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107031524,"identity":"606b439f-28a0-48a0-b1c9-a4599ede5496","added_by":"auto","created_at":"2026-04-16 03:06:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":473162,"visible":true,"origin":"","legend":"","description":"","filename":"EnhancingDataPrivacyandGovernanceinCloudDeployedLargeLanguageModelsUsingDeepLearningBasedRiskMitigation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9420186/v1_covered_b080ab31-bf3f-4076-8988-1b40954ae90e.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eEnhancing Data Privacy and Governance in Cloud-Deployed Large Language Models Using Deep Learning-Based Risk Mitigation\u003c/p\u003e","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":true,"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":"Risk Mitigation, Clouds, Dense Channel Spatial Semantic Guidance Attention, Log ID, Protection","lastPublishedDoi":"10.21203/rs.3.rs-9420186/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9420186/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe growing number of problems related to the privacy and security of data in cloud computing requires the need for efficient protection schemes. In this paper, we present an innovative solution for ensuring the privacy and management of data in large language models deployed in clouds by applying risk mitigation techniques based on deep learning. The technique involves risk mitigation, secure data management, and model performance enhancement. First, data input is acquired from a synthesized cybersecurity logs dataset and filtered using data preprocessing to eliminate any form of inconsistencies. Next, data preprocessing enables the input to be directed to the feature extraction phase utilizing the Dense Channel Spatial Semantic Guidance Attention UNet (DCSGA-UNet), which allows for the extraction of relevant features, such as Log_ID, IP_Address, Request_Type, and Response_Time_ms. After that, these features undergo processing through a Bayesian Constitutive Artificial Neural Network (BCANN) classifier that helps predict the probability of a threat or non-threat occurrence. The technique is designed using Python and evaluated against current methods. The experiments show that our innovative solution exhibits a higher accuracy of 98% in a lesser amount of time of 1.07 seconds.\u003c/p\u003e","manuscriptTitle":"Enhancing Data Privacy and Governance in Cloud-Deployed Large Language Models Using Deep Learning-Based Risk Mitigation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-16 03:05:59","doi":"10.21203/rs.3.rs-9420186/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":"2f0cdbc6-2cc7-4bdd-956f-89d0768fe736","owner":[],"postedDate":"April 16th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-16T03:05:59+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-16 03:05:59","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9420186","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9420186","identity":"rs-9420186","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}