Enhancing Practicality and Efficiency of Deepfake Detection.

Enhancing Practicality and Efficiency of 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 Article Enhancing Practicality and Efficiency of Deepfake Detection. Ismael Balafrej, Mohamed Dahmane This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4320842/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 28 Dec, 2024 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract The proliferation of deepfake generation has become increasingly widespread. Current solutions for automatically detecting and classifying generated content require substantial computational resources, making them impractical for use by the average non-expert individual particularly from edge computing applications. In this paper, we propose a series of techniques to accelerate the inference speed of deepfake detection on video data. We also draw inspiration from steganalysis approaches to expose deepfakes as any secret payloads encoded in the image. Furthermore, some key considerations were identified to significantly reduce the size of the core convolutional neural network. The experiment yielded competitive results when evaluated on two second-generation deepfake datasets, namely Celeb-DFv2 and DFDC, while requiring only a fraction of the typical computational cost and resources. Physical sciences/Mathematics and computing/Computational science Physical sciences/Mathematics and computing/Computer science Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 28 Dec, 2024 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 04 Sep, 2024 Reviews received at journal 31 Aug, 2024 Reviewers agreed at journal 12 Aug, 2024 Reviews received at journal 23 May, 2024 Reviewers agreed at journal 11 May, 2024 Reviewers invited by journal 10 May, 2024 Editor assigned by journal 10 May, 2024 Editor invited by journal 28 Apr, 2024 Submission checks completed at journal 28 Apr, 2024 First submitted to journal 24 Apr, 2024 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-4320842","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":298109206,"identity":"cc4a7b89-e6fd-41d4-ab6d-50027807fac3","order_by":0,"name":"Ismael Balafrej","email":"","orcid":"","institution":"Computer Research Institute of Montréal","correspondingAuthor":false,"prefix":"","firstName":"Ismael","middleName":"","lastName":"Balafrej","suffix":""},{"id":298109207,"identity":"e9b0bc63-c8cf-4046-94ef-e8e3fee9743b","order_by":1,"name":"Mohamed Dahmane","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA70lEQVRIiWNgGAWjYFACHhDBzMBwAMxgkGNgYGwgTYsx6VoSCaln0G3vPfjpRoU1A9/xs0c3/Nxhk94/+3DrBoYaO5xazM6cS5bOOZPOIHkmL+1m75m03BnnEttuMBxLxq3lRo6BdG7bYQaDAzlmN3jbDudu4GFsu8HYwIxPi/Hv3H9ALeffmN382/Y/3QCipR6fFjPp3AagFiDjNm/bgQSolsN4/HLGzDrnWDqP5I03Zrdl25INZ5wBakk4dhy3luM9xrdzaqzl+M7nmN1822Ynz9/D/uzGh5pqnFpggAeVm0BQwygYBaNgFIwCfAAA8f5bHu+MrnoAAAAASUVORK5CYII=","orcid":"","institution":"Computer Research Institute of Montréal","correspondingAuthor":true,"prefix":"","firstName":"Mohamed","middleName":"","lastName":"Dahmane","suffix":""}],"badges":[],"createdAt":"2024-04-25 02:10:50","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4320842/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4320842/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-024-82223-y","type":"published","date":"2024-12-28T15:57:18+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":72640775,"identity":"ecdb885c-7baf-4fd8-a399-d40637618983","added_by":"auto","created_at":"2024-12-30 16:09:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":537371,"visible":true,"origin":"","legend":"","description":"","filename":"vghgsfkqbfpzdrdkkdzxzfnqyvfntpyg.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4320842/v1_covered_8b8d5485-590f-42cf-b385-708ba1c5ee07.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhancing Practicality and Efficiency of 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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-4320842/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4320842/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The proliferation of deepfake generation has become increasingly widespread. Current solutions for automatically detecting and classifying generated content require substantial computational resources, making them impractical for use by the average non-expert individual particularly from edge computing applications. In this paper, we propose a series of techniques to accelerate the inference speed of deepfake detection on video data. We also draw inspiration from steganalysis approaches to expose deepfakes as any secret payloads encoded in the image. Furthermore, some key considerations were identified to significantly reduce the size of the core convolutional neural network. The experiment yielded competitive results when evaluated on two second-generation deepfake datasets, namely Celeb-DFv2 and DFDC, while requiring only a fraction of the typical computational cost and resources.","manuscriptTitle":"Enhancing Practicality and Efficiency of Deepfake Detection.","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-05-03 13:47:01","doi":"10.21203/rs.3.rs-4320842/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-09-04T13:10:05+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-08-31T16:16:57+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"93263383708801101093421203301497457556","date":"2024-08-12T15:44:31+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-05-23T04:50:57+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"215769918244687650317868091691083444509","date":"2024-05-11T07:55:02+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-05-11T00:25:46+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-05-11T00:17:18+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-04-28T18:40:46+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-04-28T18:39:17+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-04-24T19:45:13+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"68ff30a5-aafe-408e-b3f6-cfd097b517a2","owner":[],"postedDate":"May 3rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":31449419,"name":"Physical sciences/Mathematics and computing/Computational science"},{"id":31449420,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2024-12-30T16:04:30+00:00","versionOfRecord":{"articleIdentity":"rs-4320842","link":"https://doi.org/10.1038/s41598-024-82223-y","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2024-12-28 15:57:18","publishedOnDateReadable":"December 28th, 2024"},"versionCreatedAt":"2024-05-03 13:47:01","video":"","vorDoi":"10.1038/s41598-024-82223-y","vorDoiUrl":"https://doi.org/10.1038/s41598-024-82223-y","workflowStages":[]},"version":"v1","identity":"rs-4320842","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4320842","identity":"rs-4320842","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}