Multi Stage Spatial Temporal Ensemble Model with Integrated Learning Methods for Robust Deepfake Detection

Multi Stage Spatial Temporal Ensemble Model with Integrated Learning Methods for Robust Deepfake 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 Multi Stage Spatial Temporal Ensemble Model with Integrated Learning Methods for Robust Deepfake Detection Warusia Yassin, Faizal Abdollah, Anuar Ismail, Noor Hisham Kamis, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7131420/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract In the era of synthetic media, robust and scalable deepfake detection has become critical to preserving digital content integrity. Existing detection methods often focus narrowly on spatial or temporal features, limiting generalizability and robustness. This paper proposes an Integrated Learning Methods (ILM) Model, a novel multi-stage hybrid architecture combining YOLOv5 for precise face detection, Haar Cascade for face validation, ResNet-50 for hierarchical spatial feature extraction, LightGBM for frame-level classification, LSTM for temporal modeling, and Random Forest for final ensemble fusion. Evaluated on FaceForensics + + and Celeb-DF (v2) datasets, the proposed ILM achieved 98% accuracy, precision, recall, and F1-score, outperforming state-of-the-art CNN, RNN, and transformer-based models. Ablation studies validated the incremental contributions of each module, confirming the synergistic design of ILM in addressing spatial misalignment, temporal inconsistencies, and generalization limitations. The modular and scalable design supports deployment in digital forensics, media authentication, and AI governance, while future work will integrate transformer-based global context encoders and explainable AI for enhanced robustness and interpretability. Deepfake detection integrated learning YOLOv5 ResNet-50 LightGBM LSTM ensemble learning spatial-temporal features multi-stage framework video forensics Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 06 Nov, 2025 Reviews received at journal 06 Nov, 2025 Reviewers agreed at journal 28 Oct, 2025 Reviewers agreed at journal 16 Sep, 2025 Reviews received at journal 14 Sep, 2025 Reviewers agreed at journal 02 Sep, 2025 Reviewers invited by journal 02 Sep, 2025 Editor assigned by journal 22 Aug, 2025 Submission checks completed at journal 12 Aug, 2025 First submitted to journal 12 Aug, 2025 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-7131420","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":514780789,"identity":"d1310f5a-cd60-4348-9a38-2796a7c1f0d5","order_by":0,"name":"Warusia Yassin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA80lEQVRIiWNgGAWjYFADZgbGB1CmAdFamA0YEkjSwsDAJkGUFvkG7gRmnpp7ifPbmZ9V8/6wiWZgb94mwZhzGKcWgwO8G5h5jhUnbjjMZnabJyEtt4HnWJkE4zY8WhiAWnLYEhI3MDOAtBzObZDIMcOrRb4BpOVfQuL8ZvZvxTwJ/3Mb5N/g18IAclhuW0Jiw2EeM2aehANAW3jwazE4zLvh8N++BOMNh3mKJeekJee28aQVWyRuS8ftsPbejQ9nfEuQnd9/fOOHNzZ2uf3shzfe+LjNGrfDmIFuQxFgAxEJDM24teACdaRrGQWjYBSMguEKANPoT5FuqVqCAAAAAElFTkSuQmCC","orcid":"","institution":"Universiti Teknikal Malaysia Melaka","correspondingAuthor":true,"prefix":"","firstName":"Warusia","middleName":"","lastName":"Yassin","suffix":""},{"id":514780790,"identity":"87299d4f-dff8-4709-a94d-52d6c3141455","order_by":1,"name":"Faizal Abdollah","email":"","orcid":"","institution":"Universiti Teknikal Malaysia Melaka","correspondingAuthor":false,"prefix":"","firstName":"Faizal","middleName":"","lastName":"Abdollah","suffix":""},{"id":514780791,"identity":"cfcec248-0ab1-49e7-9314-575b8d670994","order_by":2,"name":"Anuar Ismail","email":"","orcid":"","institution":"Ask-Pentest Sdn Bhd","correspondingAuthor":false,"prefix":"","firstName":"Anuar","middleName":"","lastName":"Ismail","suffix":""},{"id":514780792,"identity":"731209e1-89b0-4dfb-bd6e-5ae641938dee","order_by":3,"name":"Noor Hisham Kamis","email":"","orcid":"","institution":"Multimedia Universiti","correspondingAuthor":false,"prefix":"","firstName":"Noor","middleName":"Hisham","lastName":"Kamis","suffix":""},{"id":514780793,"identity":"43065846-ed93-4b26-bd46-db3d49a70a25","order_by":4,"name":"Siti Fatimah Abdul Razak","email":"","orcid":"","institution":"Multimedia Universiti","correspondingAuthor":false,"prefix":"","firstName":"Siti","middleName":"Fatimah Abdul","lastName":"Razak","suffix":""},{"id":514780794,"identity":"1fa3df69-9146-4e10-98a1-157d9ff8bde9","order_by":5,"name":"Helen K Joy","email":"","orcid":"","institution":"Christ University","correspondingAuthor":false,"prefix":"","firstName":"Helen","middleName":"K","lastName":"Joy","suffix":""}],"badges":[],"createdAt":"2025-07-15 14:08:20","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7131420/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7131420/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91357486,"identity":"259961f7-ae35-4f93-b9f4-45ee8517211a","added_by":"auto","created_at":"2025-09-15 15:44:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":962616,"visible":true,"origin":"","legend":"","description":"","filename":"EnhancedDeepfakeDetectionThroughIntegratedLearningMethodsFINALVERSIONv2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7131420/v1_covered_a0c6682f-0fb4-405b-9265-aa4f905bdd20.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multi Stage Spatial Temporal Ensemble Model with Integrated Learning Methods for Robust Deepfake Detection","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":"discover-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Computing](https://link.springer.com/journal/10791)","snPcode":"10791","submissionUrl":"https://submission.springernature.com/new-submission/10791/3","title":"Discover Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Deepfake detection, integrated learning, YOLOv5, ResNet-50, LightGBM, LSTM, ensemble learning, spatial-temporal features, multi-stage framework, video forensics","lastPublishedDoi":"10.21203/rs.3.rs-7131420/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7131420/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn the era of synthetic media, robust and scalable deepfake detection has become critical to preserving digital content integrity. Existing detection methods often focus narrowly on spatial or temporal features, limiting generalizability and robustness. This paper proposes an Integrated Learning Methods (ILM) Model, a novel multi-stage hybrid architecture combining YOLOv5 for precise face detection, Haar Cascade for face validation, ResNet-50 for hierarchical spatial feature extraction, LightGBM for frame-level classification, LSTM for temporal modeling, and Random Forest for final ensemble fusion. Evaluated on FaceForensics\u0026thinsp;+\u0026thinsp;+\u0026thinsp;and Celeb-DF (v2) datasets, the proposed ILM achieved 98% accuracy, precision, recall, and F1-score, outperforming state-of-the-art CNN, RNN, and transformer-based models. Ablation studies validated the incremental contributions of each module, confirming the synergistic design of ILM in addressing spatial misalignment, temporal inconsistencies, and generalization limitations. The modular and scalable design supports deployment in digital forensics, media authentication, and AI governance, while future work will integrate transformer-based global context encoders and explainable AI for enhanced robustness and interpretability.\u003c/p\u003e","manuscriptTitle":"Multi Stage Spatial Temporal Ensemble Model with Integrated Learning Methods for Robust Deepfake Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-15 15:20:14","doi":"10.21203/rs.3.rs-7131420/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-11-06T14:22:33+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-06T10:56:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"24426595134822719569094415077682691405","date":"2025-10-28T05:28:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"328217705199407290981344273385715470536","date":"2025-09-16T09:56:51+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-14T09:34:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"299575873915328008631997073203682790998","date":"2025-09-02T10:43:12+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-02T06:15:41+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-23T03:16:47+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-12T14:33:47+00:00","index":"","fulltext":""},{"type":"submitted","content":"Discover Computing","date":"2025-08-12T14:29:45+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"discover-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Discover Computing](https://link.springer.com/journal/10791)","snPcode":"10791","submissionUrl":"https://submission.springernature.com/new-submission/10791/3","title":"Discover Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"9a280e6f-9d7a-4546-9b5f-10eb1de012e2","owner":[],"postedDate":"September 15th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-01T15:38:58+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-15 15:20:14","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7131420","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7131420","identity":"rs-7131420","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}