NAC: Noise-Adaptive Correction for Robust Graph Neural Networks toward Trusted Graph Computing

NAC: Noise-Adaptive Correction for Robust Graph Neural Networks toward Trusted Graph Computing | 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 NAC: Noise-Adaptive Correction for Robust Graph Neural Networks toward Trusted Graph Computing Hwan Kim, Jiha Kim, Seunghyun Park, Hyunhee Park This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9264474/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Trusted computing systems and blockchain-enabled security applications increas- ingly rely on Graph Neural Networks (GNNs) for trust graph analysis, fraud detection, and anomaly identification. In these security-critical deployments, graph data is routinely subject to adversarial manipulation—including Sybil attacks, attribute poisoning, and label flipping—making robustness a fundamen- tal system-level trust requirement. While GNNs achieve strong performance on homophilic graph data such as citation networks, in compound noise environ- ments where structural and feature noise are combined, attention mechanisms become distorted and performance degrades severely. Existing studies either rely on structure learning that requires high computational cost of O(N2) or need clean validation data, limiting practical applicability in real-world trusted com- puting deployments. In this paper, we propose NAC (Noise-Adaptive Corrector), a framework that leverages homophily properties to simultaneously achieve com- putational efficiency and robustness. Inspired by trusted computing principles, NAC employs a dual-path architecture that separates a trusted reference signal path from an observed noisy path, using KL divergence to quantify trust deviation at the node level. NAC actively detects and corrects noise without label infor- mation by minimizing the KL divergence between reference signals generated through neighbor averaging and observed signals. Furthermore, we introduce a buffering strategy that omits the Reference Encoder computation during infer- ence, reducing actual computational load by approximately 50%. Experimental results on various benchmark datasets show that the proposed NAC-Practical achieves 6.2%p improved accuracy over baseline models without requiring clean original data, demonstrating superior robustness and establishing a foundation for trustworthy GNN deployment in blockchain-enabled security systems. Graph Neural Networks Noise Robustness KL Divergence Adaptive Correction Trusted Computing Blockchain Security Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 20 Apr, 2026 Reviewers agreed at journal 19 Apr, 2026 Reviewers agreed at journal 17 Apr, 2026 Reviewers invited by journal 16 Apr, 2026 Editor assigned by journal 01 Apr, 2026 Submission checks completed at journal 01 Apr, 2026 First submitted to journal 30 Mar, 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-9264474","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":625965753,"identity":"8400c01f-dd72-4cd5-8b4c-f0dab2a7bddf","order_by":0,"name":"Hwan Kim","email":"","orcid":"","institution":"Myongji University","correspondingAuthor":false,"prefix":"","firstName":"Hwan","middleName":"","lastName":"Kim","suffix":""},{"id":625965754,"identity":"659d340f-7877-4b77-8f1d-1b328dbad6b7","order_by":1,"name":"Jiha Kim","email":"","orcid":"","institution":"Myongji University","correspondingAuthor":false,"prefix":"","firstName":"Jiha","middleName":"","lastName":"Kim","suffix":""},{"id":625965755,"identity":"d7b90c44-b361-4f6b-83ec-ba9ddb50a304","order_by":2,"name":"Seunghyun Park","email":"","orcid":"","institution":"Hansung University","correspondingAuthor":false,"prefix":"","firstName":"Seunghyun","middleName":"","lastName":"Park","suffix":""},{"id":625965756,"identity":"f855068c-8631-42af-a931-926a8cbff069","order_by":3,"name":"Hyunhee Park","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuklEQVRIiWNgGAWjYBACAwkQecCGgbEBzE8gWksa6VoOw/hEaDGX7j34ueLM+WjmGQmMH34wpOUT1GI551yy5Jkbt3MbZyQwS/Yw5Fg2EHTYjRwDyYYPYC0M0gwMFQYEbQFqMf7Z8OEc2JbfxGoxk2y4cQCkhQ1oSw4xWvLSLBvOJOc29jxss+wxSCNGS+7hmw3H7HI3ticfvvGjIpmwFgYGHghl2ACKTGI0wLXIE6V4FIyCUTAKRiQAAD0XQUgKfRwBAAAAAElFTkSuQmCC","orcid":"","institution":"Myongji University","correspondingAuthor":true,"prefix":"","firstName":"Hyunhee","middleName":"","lastName":"Park","suffix":""}],"badges":[],"createdAt":"2026-03-30 08:53:59","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9264474/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9264474/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107707585,"identity":"2630c053-c0f3-4de7-876b-12bc52b5d958","added_by":"auto","created_at":"2026-04-24 09:20:40","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4608916,"visible":true,"origin":"","legend":"","description":"","filename":"nacsubmission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9264474/v1_covered_30997ab6-5eaa-446d-8e5e-db0687c75985.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"NAC: Noise-Adaptive Correction for Robust Graph Neural Networks toward Trusted Graph Computing","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"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":"Graph Neural Networks, Noise Robustness, KL Divergence, Adaptive Correction, Trusted Computing, Blockchain Security","lastPublishedDoi":"10.21203/rs.3.rs-9264474/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9264474/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Trusted computing systems and blockchain-enabled security applications increas- ingly rely on Graph Neural Networks (GNNs) for trust graph analysis, fraud detection, and anomaly identification. In these security-critical deployments, graph data is routinely subject to adversarial manipulation—including Sybil attacks, attribute poisoning, and label flipping—making robustness a fundamen- tal system-level trust requirement. While GNNs achieve strong performance on homophilic graph data such as citation networks, in compound noise environ- ments where structural and feature noise are combined, attention mechanisms become distorted and performance degrades severely. Existing studies either rely on structure learning that requires high computational cost of O(N2) or need clean validation data, limiting practical applicability in real-world trusted com- puting deployments. In this paper, we propose NAC (Noise-Adaptive Corrector), a framework that leverages homophily properties to simultaneously achieve com- putational efficiency and robustness. Inspired by trusted computing principles, NAC employs a dual-path architecture that separates a trusted reference signal path from an observed noisy path, using KL divergence to quantify trust deviation at the node level. NAC actively detects and corrects noise without label infor- mation by minimizing the KL divergence between reference signals generated through neighbor averaging and observed signals. Furthermore, we introduce a buffering strategy that omits the Reference Encoder computation during infer- ence, reducing actual computational load by approximately 50%. Experimental results on various benchmark datasets show that the proposed NAC-Practical achieves 6.2%p improved accuracy over baseline models without requiring clean original data, demonstrating superior robustness and establishing a foundation for trustworthy GNN deployment in blockchain-enabled security systems.","manuscriptTitle":"NAC: Noise-Adaptive Correction for Robust Graph Neural Networks toward Trusted Graph Computing","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-23 10:46:00","doi":"10.21203/rs.3.rs-9264474/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"134955711193819417642596889302919201531","date":"2026-04-20T04:43:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"1743077170308128734809690369719428044","date":"2026-04-20T01:49:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"247654659390760631830786310178079317807","date":"2026-04-17T06:39:59+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-17T03:40:11+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-01T07:46:20+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-01T07:46:13+00:00","index":"","fulltext":""},{"type":"submitted","content":"Discover Computing","date":"2026-03-30T08:43:40+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":"f0b9150f-0b00-410e-a379-9943720d71d7","owner":[],"postedDate":"April 23rd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-13T09:08:50+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-23 10:46:00","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9264474","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9264474","identity":"rs-9264474","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}