Multimodal Advanced Persistent Threat Detection and Attribution Using Heterogenous Graph Neural Network and Analysis Using Explainable AI

preprint OA: closed CC-BY-4.0
📄 Open PDF Full text JSON View at publisher

Abstract

Abstract Attributing cyberattacks to specific threat actors remains a critical yet complex challenge in cybersecurity. We propose a robust and interpretable framework for cyber threat attribution using a Heterogeneous Graph Neural Network (HGNN) approach that integrates static and behavioral malware analysis, threat intelli- gence from VirusTotal, and associations with Advanced Persistent Threat (APT) groups. The pipeline begins by extracting hash-level threat intelligence from a malware dataset and generating enriched sub-datasets (e.g., APT groups, entry points, libraries), which are then merged into a unified heterogeneous graph. Ini- tial experiments using traditional Random Forest classifiers yielded an accuracy of 58.09However, leveraging HGNN allowed us to capture the relational structure between malware artifacts and threat actor tactics, achieving a notable accu- racy of 98.52The model also supports anomaly detection, cross-platform malware analysis, and explainable AI (SHAP) interpretation to enhance traceability and trust. Our approach achieved an F1-score of 97.88, an AUC-ROC of 98.89, and a training stability of 0.92, laying the foundation for predictive cyber threat intelligence systems across multiple platforms.
Full text 24,890 characters · extracted from preprint-html · click to expand
Multimodal Advanced Persistent Threat Detection and Attribution Using Heterogenous Graph Neural Network and Analysis Using Explainable AI | 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 Multimodal Advanced Persistent Threat Detection and Attribution Using Heterogenous Graph Neural Network and Analysis Using Explainable AI Premanand Ghadekar, Sai Kulkarni, Pranav Jadhav, Isha Kulkarni, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6636364/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 Attributing cyberattacks to specific threat actors remains a critical yet complex challenge in cybersecurity. We propose a robust and interpretable framework for cyber threat attribution using a Heterogeneous Graph Neural Network (HGNN) approach that integrates static and behavioral malware analysis, threat intelli- gence from VirusTotal, and associations with Advanced Persistent Threat (APT) groups. The pipeline begins by extracting hash-level threat intelligence from a malware dataset and generating enriched sub-datasets (e.g., APT groups, entry points, libraries), which are then merged into a unified heterogeneous graph. Ini- tial experiments using traditional Random Forest classifiers yielded an accuracy of 58.09However, leveraging HGNN allowed us to capture the relational structure between malware artifacts and threat actor tactics, achieving a notable accu- racy of 98.52The model also supports anomaly detection, cross-platform malware analysis, and explainable AI (SHAP) interpretation to enhance traceability and trust. Our approach achieved an F1-score of 97.88, an AUC-ROC of 98.89, and a training stability of 0.92, laying the foundation for predictive cyber threat intelligence systems across multiple platforms. Cyber Attack APT Graph Neural Network Heterogenous Graph Neural Network Multimodal Explainable AI Threat Detection Anomaly prediction 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-6636364","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":527205874,"identity":"88448a76-5f3b-4712-b401-e7912f6b144a","order_by":0,"name":"Premanand Ghadekar","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDklEQVRIie3RwUrDMBjA8YxCd0nJtaMUX6Ej0FLQ+SorgZz6AAEFA0JOc1476CsIO3rMKM5LHmCld09VehJEpqbIbkuZNw/5k0AI/MIHAcBm+8eNOIBArzkAYw7k783JBEog5d+Ir/cQSYLqaf3xOAs5eth0LaNnyaqdVh04D9fyOEmXlNZ3imDuv5FJqfJp2eSRHoxiE4kUjHeecDLuqyjwBBsVAZ1rUmVmgt7rvbjpCf70vthlMdn25HuAQLfxRJVxtIgDj+dZ4TtSE2kk6cKNm1A8Y+HDOC23lBSQSKkiglcGkkDnpX4VV+E9UnjXXpOLYry57RibhUvTYIeD23/HkfsBApDhUZvNZrP9AIUpaQkNmDJNAAAAAElFTkSuQmCC","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Premanand","middleName":"","lastName":"Ghadekar","suffix":""},{"id":527205878,"identity":"0362c761-0a92-4ba0-8915-f6e35572e408","order_by":1,"name":"Sai Kulkarni","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Sai","middleName":"","lastName":"Kulkarni","suffix":""},{"id":527205879,"identity":"2cf01aa6-6ab6-4193-8c31-eb11c7ad0567","order_by":2,"name":"Pranav Jadhav","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Pranav","middleName":"","lastName":"Jadhav","suffix":""},{"id":527205880,"identity":"fecd620b-b7f8-4c23-a33e-2603ca1dab0d","order_by":3,"name":"Isha Kulkarni","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Isha","middleName":"","lastName":"Kulkarni","suffix":""},{"id":527205881,"identity":"6d103c87-e5be-448d-851e-f3a996ff8518","order_by":4,"name":"Om Lohade","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Om","middleName":"","lastName":"Lohade","suffix":""},{"id":527205883,"identity":"104a581a-dee4-4740-896a-2a48c26b7ce4","order_by":5,"name":"Isha Mahajan","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Isha","middleName":"","lastName":"Mahajan","suffix":""}],"badges":[],"createdAt":"2025-05-10 18:38:05","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6636364/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6636364/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93191481,"identity":"33d9bbb3-de09-4aab-aa9c-0ce896919ed5","added_by":"auto","created_at":"2025-10-10 04:22:21","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":920362,"visible":true,"origin":"","legend":"","description":"","filename":"NewSpringerMultimodalCyberAttackFinal.docx","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/88ae5ff66618c5bdc6e01f21.docx"},{"id":93191466,"identity":"30d2fd76-57bc-4aea-9a53-45b6fc63b0cf","added_by":"auto","created_at":"2025-10-10 04:22:21","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7178,"visible":true,"origin":"","legend":"","description":"","filename":"d9597a5725bf4c5f8d941af00428be90.json","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/e2d4139b00c6227000c6f9cd.json"},{"id":93191471,"identity":"c3288791-3526-474d-b54f-51686adfca3d","added_by":"auto","created_at":"2025-10-10 04:22:21","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":95459,"visible":true,"origin":"","legend":"","description":"","filename":"d9597a5725bf4c5f8d941af00428be901enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/505bfc62b032057aaacf92bc.xml"},{"id":93191916,"identity":"a1a4232c-1819-4819-9a4f-fe459ce87d7a","added_by":"auto","created_at":"2025-10-10 04:30:21","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":53826,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/287ce25be47573ce35d6adf9.png"},{"id":93191918,"identity":"2b1d4eff-3770-45c6-b389-17933514e996","added_by":"auto","created_at":"2025-10-10 04:30:21","extension":"jpeg","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":595636,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage10.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/d81a5690eb955210caeb6701.jpeg"},{"id":93191468,"identity":"fda9fd50-825f-430a-b62d-7928f54a8b4d","added_by":"auto","created_at":"2025-10-10 04:22:21","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21750,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage11.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/b0122ffe21c920d6126adb22.jpeg"},{"id":93191917,"identity":"a4a3a823-fc8f-4def-be66-94d0e888eb97","added_by":"auto","created_at":"2025-10-10 04:30:21","extension":"jpeg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":44823,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage12.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/aaf7a3b9054c3d1fe09954ab.jpeg"},{"id":93191470,"identity":"55c8559b-f88f-4e57-9d32-068c6b050b20","added_by":"auto","created_at":"2025-10-10 04:22:21","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":24586,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage13.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/4f446c99744b0ad8787c1d1c.png"},{"id":93191921,"identity":"b6ec4fc7-c81a-4628-a3e5-f304cc3d64ca","added_by":"auto","created_at":"2025-10-10 04:30:21","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20530,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage14.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/b7f23972b8a3e5e16a181bbb.png"},{"id":93191474,"identity":"fdef92d2-f46f-472b-81a5-82ed913c369e","added_by":"auto","created_at":"2025-10-10 04:22:21","extension":"emf","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":347344,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.emf","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/a9da3feba5ebb5958a350eb8.emf"},{"id":93191922,"identity":"e628f92f-e01e-4a7d-a8db-79bd261fbadc","added_by":"auto","created_at":"2025-10-10 04:30:21","extension":"jpeg","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":312821,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/96907d6d477b750e16f02aa7.jpeg"},{"id":93191482,"identity":"a80bbd7a-d991-4437-b528-de2cec26df54","added_by":"auto","created_at":"2025-10-10 04:22:21","extension":"jpeg","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":54795,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/3a44b9a1b89f7905b2534c0d.jpeg"},{"id":93191919,"identity":"7d3b637e-efe1-425d-a3ea-e234ab7d668b","added_by":"auto","created_at":"2025-10-10 04:30:21","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37825,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/089068e0cdf075c970c6c03c.png"},{"id":93191475,"identity":"9399a962-983b-425b-9402-6ed0f17128c4","added_by":"auto","created_at":"2025-10-10 04:22:21","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":142528,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/23bbde2266027e61763e31be.png"},{"id":93191479,"identity":"76f8adaf-4903-4e0e-acea-7c39f8237e17","added_by":"auto","created_at":"2025-10-10 04:22:21","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":26471,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/7cd9f7a11fb2464b0b050288.png"},{"id":93192326,"identity":"d637dd56-e79c-49d3-89a5-ae9703d0e3b2","added_by":"auto","created_at":"2025-10-10 04:38:21","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":97312,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/488770288f00cb5d985b3576.png"},{"id":93191489,"identity":"7bdaf371-e01a-4978-b57a-9ac4cda3bedf","added_by":"auto","created_at":"2025-10-10 04:22:21","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":153135,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/24fcb344be01b28da15a9133.png"},{"id":93191476,"identity":"13ad5ce0-4ae9-4e4c-9796-3c53e3d0c763","added_by":"auto","created_at":"2025-10-10 04:22:21","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12179,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/00733f1889359710eefb7b29.png"},{"id":93191488,"identity":"607f2f34-62e6-4056-aa8a-978cbb52b2fc","added_by":"auto","created_at":"2025-10-10 04:22:21","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":365339,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/4bd338c89d3791455d6feb23.png"},{"id":93191498,"identity":"d439e2ae-d178-458a-9af0-fe161ae60802","added_by":"auto","created_at":"2025-10-10 04:22:22","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7020,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage11.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/abf547a0dba993bd3b435cab.png"},{"id":93191493,"identity":"50cded73-7292-4b3e-b40a-e12eeb8c8825","added_by":"auto","created_at":"2025-10-10 04:22:22","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12165,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage12.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/fa4f622ce328758f8f14cf6e.png"},{"id":93191492,"identity":"5ed85f90-e517-4db7-b1b1-40c9ba365cde","added_by":"auto","created_at":"2025-10-10 04:22:22","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7893,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage13.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/14c86954438604889b64e31a.png"},{"id":93192329,"identity":"f5d41635-8161-48d2-8f77-f3b600630437","added_by":"auto","created_at":"2025-10-10 04:38:21","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6653,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage14.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/3cd3908f03abc2b9b66df9d2.png"},{"id":93191497,"identity":"11502ec2-36ce-4f9d-98cf-63f8d3e3855c","added_by":"auto","created_at":"2025-10-10 04:22:22","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":161500,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/2ca4493445f6cc045863a4c8.png"},{"id":93191485,"identity":"b7391980-1a68-447e-a22c-e0df44e5a960","added_by":"auto","created_at":"2025-10-10 04:22:21","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":78511,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/f2d7e531771c2b1d648b538c.png"},{"id":93191926,"identity":"d33f1697-473e-4692-b860-ae3f47717f38","added_by":"auto","created_at":"2025-10-10 04:30:22","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":11540,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/2cce4bd358f1c6e52e3545db.png"},{"id":93191491,"identity":"0762899d-561b-401c-b41a-17a136c4aaa6","added_by":"auto","created_at":"2025-10-10 04:22:22","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15822,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/75d207daa7d2dbfc5083a92e.png"},{"id":93191495,"identity":"831990e8-6a48-47a4-91dc-1d691705fe8c","added_by":"auto","created_at":"2025-10-10 04:22:22","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":78959,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/84436127e2bad2dfb6f1b3ac.png"},{"id":93191490,"identity":"fd844e0d-e0f1-449d-8929-664a31b589da","added_by":"auto","created_at":"2025-10-10 04:22:21","extension":"png","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9795,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/b5dd62df89b3907bd9aa0516.png"},{"id":93191923,"identity":"7c4d2f00-c37e-49c7-9e06-b64bd22f287b","added_by":"auto","created_at":"2025-10-10 04:30:21","extension":"png","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":53902,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/e9ccbb7b8936ca358f7ae82f.png"},{"id":93191924,"identity":"1b949660-b861-4f6d-9e24-e5c25c5e51cd","added_by":"auto","created_at":"2025-10-10 04:30:21","extension":"png","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":38717,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/8b45258f2672bc729df2b304.png"},{"id":93191486,"identity":"930bb287-c9f2-4baf-8f02-33b6ea254295","added_by":"auto","created_at":"2025-10-10 04:22:21","extension":"xml","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":89511,"visible":true,"origin":"","legend":"","description":"","filename":"d9597a5725bf4c5f8d941af00428be901structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/e4132518ff6a4b1b28698ad9.xml"},{"id":93191499,"identity":"024580c3-8758-422b-899f-183f7c8e3a68","added_by":"auto","created_at":"2025-10-10 04:22:22","extension":"html","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":105276,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1/8bb4e6ed80adce7b3b9eed06.html"},{"id":95657414,"identity":"610f75a8-c35c-410d-a957-4ab2e26746db","added_by":"auto","created_at":"2025-11-11 16:20:46","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":992753,"visible":true,"origin":"","legend":"","description":"","filename":"NewSpringerMultimodalCyberAttackFinal.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6636364/v1_covered_f5e0d5b4-76b7-46f3-b273-03c7965a43d0.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multimodal Advanced Persistent Threat Detection and Attribution Using Heterogenous Graph Neural Network and Analysis Using Explainable AI","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Cyber Attack, APT, Graph Neural Network, Heterogenous Graph Neural Network, Multimodal, Explainable AI, Threat Detection, Anomaly prediction","lastPublishedDoi":"10.21203/rs.3.rs-6636364/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6636364/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAttributing cyberattacks to specific threat actors remains a critical yet complex challenge in cybersecurity. We propose a robust and interpretable framework for cyber threat attribution using a Heterogeneous Graph Neural Network (HGNN) approach that integrates static and behavioral malware analysis, threat intelli- gence from VirusTotal, and associations with Advanced Persistent Threat (APT) groups. The pipeline begins by extracting hash-level threat intelligence from a malware dataset and generating enriched sub-datasets (e.g., APT groups, entry points, libraries), which are then merged into a unified heterogeneous graph. Ini- tial experiments using traditional Random Forest classifiers yielded an accuracy of 58.09However, leveraging HGNN allowed us to capture the relational structure between malware artifacts and threat actor tactics, achieving a notable accu- racy of 98.52The model also supports anomaly detection, cross-platform malware analysis, and explainable AI (SHAP) interpretation to enhance traceability and trust. Our approach achieved an F1-score of 97.88, an AUC-ROC of 98.89, and a training stability of 0.92, laying the foundation for predictive cyber threat intelligence systems across multiple platforms.\u003c/p\u003e","manuscriptTitle":"Multimodal Advanced Persistent Threat Detection and Attribution Using Heterogenous Graph Neural Network and Analysis Using Explainable AI","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-10 04:22:16","doi":"10.21203/rs.3.rs-6636364/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":"d231f45b-5f0e-4f28-aee2-b6061ecb816c","owner":[],"postedDate":"October 10th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-11-11T13:54:03+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-10 04:22:16","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6636364","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6636364","identity":"rs-6636364","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00
unpaywall
last seen: 2026-05-24T02:00:01.246996+00:00
License: CC-BY-4.0