A Cross-Modal Attention for Detecting Hidden Online Gambling Promotion in Multilingual Multimodal Watermarked Advertising Images

A Cross-Modal Attention for Detecting Hidden Online Gambling Promotion in Multilingual Multimodal Watermarked Advertising Images | 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 A Cross-Modal Attention for Detecting Hidden Online Gambling Promotion in Multilingual Multimodal Watermarked Advertising Images Abdul Azzam Ajhari, Rizal Fathoni Aji, Aprinaldi Jasa Mantau, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8925590/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 Online gambling operators increasingly evade regulation by concealing promotional content within watermarked advertising images across social media and compromised domains. Traditional text-centric monitoring fails in these scenarios, particularly in multilingual environments where visual obfuscation masks critical semantic cues. This paper proposes a robust hybrid multimodal framework that explicitly models fine-grained interactions between OCR-extracted text and visual structures. Our architecture leverages a Vision Transformer (ViT) for spatial feature encoding and XLM-RoBERTa for cross-lingual semantic representation, integrated via a text-guided cross-modal attention (CMA) mechanism. This allows the model to "attend" to specific image regions based on extracted textual tokens, effectively uncovering hidden promotional signals. Testing on a newly curated dataset of 4,485 manually verified multilingual screenshots, the framework achieves an Accuracy of 0.9947 and an F1-score of 0.9947, consistently outperforming late-fusion baselines while maintaining performance comparable to the strongest unimodal configuration. Our findings reveal that while visual cues provide strong complementary discriminative signals, CMA ensures robustness against OCR noise and linguistic variation. This study provides a scalable, high-precision solution for cross-border regulatory monitoring in adversarial digital ecosystems. online gambling detection multimodal learning cross-modal attention multilingual OCR Vision Transformer XLM-RoBERTa Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 15 Mar, 2026 Reviews received at journal 15 Mar, 2026 Reviewers agreed at journal 11 Mar, 2026 Reviews received at journal 05 Mar, 2026 Reviewers agreed at journal 27 Feb, 2026 Reviewers agreed at journal 25 Feb, 2026 Reviewers invited by journal 25 Feb, 2026 Editor assigned by journal 22 Feb, 2026 Submission checks completed at journal 22 Feb, 2026 First submitted to journal 20 Feb, 2026 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-8925590","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":596762423,"identity":"5781b1ff-32a3-4d7f-81f5-953d0c0d3b37","order_by":0,"name":"Abdul Azzam Ajhari","email":"","orcid":"","institution":"University of Indonesia","correspondingAuthor":false,"prefix":"","firstName":"Abdul","middleName":"Azzam","lastName":"Ajhari","suffix":""},{"id":596762424,"identity":"d122c676-9a2c-4090-a289-0a9e49a292ff","order_by":1,"name":"Rizal Fathoni Aji","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvUlEQVRIiWNgGAWjYDACZiB+UAFiMTaASB6GA8RoSThDkhYQSGxD5hHSYt7O/vBD4jw7ewaJ5AaGHzUMMnyEtMgcZkiWSNyWnNggkdjA2HOMgUeSkBYJZoYDQC0HEhiAWhh4Gxh4DAhrYWz+kTjngD1IC+Nf4rQwswEVH2AEOYyZSFvY2CwSjiUntvE8bDgsc0yCCL/wH39840ONnT0/e/rDh29qbOwJhhgcsDGAY0SCWPWjYBSMglEwCvABAB+YN/BFrNScAAAAAElFTkSuQmCC","orcid":"","institution":"University of Indonesia","correspondingAuthor":true,"prefix":"","firstName":"Rizal","middleName":"Fathoni","lastName":"Aji","suffix":""},{"id":596762425,"identity":"73fb1619-c541-4790-9a61-c62aba9e4fb5","order_by":2,"name":"Aprinaldi Jasa Mantau","email":"","orcid":"","institution":"University of Indonesia","correspondingAuthor":false,"prefix":"","firstName":"Aprinaldi","middleName":"Jasa","lastName":"Mantau","suffix":""},{"id":596762426,"identity":"5b492829-81fb-40e0-9d79-44edf69c1bc8","order_by":3,"name":"Wisnu Jatmiko","email":"","orcid":"","institution":"University of Indonesia","correspondingAuthor":false,"prefix":"","firstName":"Wisnu","middleName":"","lastName":"Jatmiko","suffix":""},{"id":596762427,"identity":"0689c120-2ac4-4e9d-9745-56096939cd4f","order_by":4,"name":"Mahardhika Pratama","email":"","orcid":"","institution":"University of South Australia","correspondingAuthor":false,"prefix":"","firstName":"Mahardhika","middleName":"","lastName":"Pratama","suffix":""}],"badges":[],"createdAt":"2026-02-20 11:53:44","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8925590/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8925590/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104398448,"identity":"e1622bd0-b256-498d-80a9-0d86564906ab","added_by":"auto","created_at":"2026-03-11 12:02:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1291652,"visible":true,"origin":"","legend":"","description":"","filename":"AAAJKSUCISExperiment.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8925590/v1_covered_c535c0b3-4557-4153-a78c-1aa37955a7ff.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Cross-Modal Attention for Detecting Hidden Online Gambling Promotion in Multilingual Multimodal Watermarked Advertising Images","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":"journal-of-king-saud-university-computer-and-information-sciences","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Journal of King Saud University Computer and Information Sciences](https://link.springer.com/journal/44443)","snPcode":"44443","submissionUrl":"https://submission.springernature.com/new-submission/44443/3","title":"Journal of King Saud University Computer and Information Sciences","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"online gambling detection, multimodal learning, cross-modal attention, multilingual OCR, Vision Transformer, XLM-RoBERTa","lastPublishedDoi":"10.21203/rs.3.rs-8925590/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8925590/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eOnline gambling operators increasingly evade regulation by concealing promotional content within watermarked advertising images across social media and compromised domains. Traditional text-centric monitoring fails in these scenarios, particularly in multilingual environments where visual obfuscation masks critical semantic cues. This paper proposes a robust hybrid multimodal framework that explicitly models fine-grained interactions between OCR-extracted text and visual structures. Our architecture leverages a Vision Transformer (ViT) for spatial feature encoding and XLM-RoBERTa for cross-lingual semantic representation, integrated via a text-guided cross-modal attention (CMA) mechanism. This allows the model to \"attend\" to specific image regions based on extracted textual tokens, effectively uncovering hidden promotional signals. Testing on a newly curated dataset of 4,485 manually verified multilingual screenshots, the framework achieves an Accuracy of 0.9947 and an F1-score of 0.9947, consistently outperforming late-fusion baselines while maintaining performance comparable to the strongest unimodal configuration. Our findings reveal that while visual cues provide strong complementary discriminative signals, CMA ensures robustness against OCR noise and linguistic variation. This study provides a scalable, high-precision solution for cross-border regulatory monitoring in adversarial digital ecosystems.\u003c/p\u003e","manuscriptTitle":"A Cross-Modal Attention for Detecting Hidden Online Gambling Promotion in Multilingual Multimodal Watermarked Advertising Images","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-27 06:09:42","doi":"10.21203/rs.3.rs-8925590/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-15T10:15:25+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-15T09:14:19+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"339630017576680118699762161918511819191","date":"2026-03-11T07:45:49+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-05T08:23:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"244946468049642565506906937195437761931","date":"2026-02-27T07:47:27+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"200009065828066883509103181431198859804","date":"2026-02-25T07:14:21+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-25T07:05:45+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-23T02:32:23+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-23T02:30:14+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of King Saud University Computer and Information Sciences","date":"2026-02-20T11:50:46+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-king-saud-university-computer-and-information-sciences","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Journal of King Saud University Computer and Information Sciences](https://link.springer.com/journal/44443)","snPcode":"44443","submissionUrl":"https://submission.springernature.com/new-submission/44443/3","title":"Journal of King Saud University Computer and Information Sciences","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"f92b756a-9bfd-45d3-9ef3-c8f0013c2e75","owner":[],"postedDate":"February 27th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-01T06:24:45+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-27 06:09:42","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8925590","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8925590","identity":"rs-8925590","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}