Evaluating the effectiveness of neuron coverage metrics: a metamorphic-testing approach

Evaluating the effectiveness of neuron coverage metrics: a metamorphic-testing approach | 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 Evaluating the effectiveness of neuron coverage metrics: a metamorphic-testing approach Zenghui Zhou, Pak-Lok Poon, Tsong Yueh Chen, Kun Qiu, Qinghua Zhou, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4660114/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 31 Mar, 2025 Read the published version in Software Quality Journal → Version 1 posted 9 You are reading this latest preprint version Abstract Deep neural networks (DNNs) are now widely used in many sectors of our society. This phenomenon also means that if these DNNs contain faults, they will have profound adverse impacts on our daily lives. Thus, DNNs have to be comprehensively tested for ''correctness'' before they are released for use.Since such testing involves the use of a DNN test set, the comprehensiveness of this test set is of utmost importance. Until now, many researchers have proposed their own neuron-coverage (NC) metrics to measure the comprehensiveness of a DNN test set. However, their studies solely focused on those DNN testing scenarios with the presence of a test oracle. We observed that, in reality, there are many DNN testing scenarios where a test oracle does not exist and, therefore, the results of all previous studies may be inapplicable to these testing scenarios.Inspired by this observation, we have performed an empirical study to investigate the usefulness of some common and major NC metrics in terms of correlation analysis and invariability analysis. Our experiment results showed that, on the one hand, some NC metrics are useful measures of DNN test-set comprehensiveness (in terms of correlation analysis), but on the other hand, these metrics are not robust enough (in terms of invariability analysis). deep learning system deep neural network machine learning metamorphic relation metamorphic testing neuron coverage Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 31 Mar, 2025 Read the published version in Software Quality Journal → Version 1 posted Editorial decision: Revision requested 20 Oct, 2024 Reviews received at journal 18 Oct, 2024 Reviews received at journal 31 Aug, 2024 Reviewers agreed at journal 07 Aug, 2024 Reviewers agreed at journal 05 Aug, 2024 Reviewers invited by journal 05 Aug, 2024 Editor assigned by journal 01 Jul, 2024 Submission checks completed at journal 01 Jul, 2024 First submitted to journal 29 Jun, 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-4660114","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":329035977,"identity":"9c85ee95-f171-4ce3-8e5b-d2b06f3f38d2","order_by":0,"name":"Zenghui Zhou","email":"","orcid":"","institution":"Beihang University","correspondingAuthor":false,"prefix":"","firstName":"Zenghui","middleName":"","lastName":"Zhou","suffix":""},{"id":329035979,"identity":"085b7955-d55b-46b2-9ccf-063526c433f0","order_by":1,"name":"Pak-Lok Poon","email":"","orcid":"","institution":"Central Queensland University","correspondingAuthor":false,"prefix":"","firstName":"Pak-Lok","middleName":"","lastName":"Poon","suffix":""},{"id":329035981,"identity":"7a846432-e055-4ae4-a76e-d6408256e6c1","order_by":2,"name":"Tsong Yueh Chen","email":"","orcid":"","institution":"Swinburne University of Technolog","correspondingAuthor":false,"prefix":"","firstName":"Tsong","middleName":"Yueh","lastName":"Chen","suffix":""},{"id":329035982,"identity":"3e1459a1-0a0b-40bf-92c7-be081260a99b","order_by":3,"name":"Kun Qiu","email":"","orcid":"","institution":"Hefei University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Kun","middleName":"","lastName":"Qiu","suffix":""},{"id":329035983,"identity":"234da06d-8ace-4a13-9668-f5010110983e","order_by":4,"name":"Qinghua Zhou","email":"","orcid":"","institution":"Beihang University","correspondingAuthor":false,"prefix":"","firstName":"Qinghua","middleName":"","lastName":"Zhou","suffix":""},{"id":329035984,"identity":"f591b179-811b-4b0a-878d-2f808d965761","order_by":5,"name":"Zheng Zheng","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1UlEQVRIiWNgGAWjYDACCTBpkwDhsRGvJY10LYdJ0CI/u/nYwy9/zucZHD/8gOFD2WEG/tkN+LUwzjmWbizDc7vY4EyaAeOMc4cZJO4cwK+FWSLHTFpC4nbihgMJBsy8bYcZDCQS8Gthk8j/Ji1hcC5xw/nnH5j/EqOFRyKHTfJDwoHEDTdyDJgZidEiIZFmJs1wILlY8sabgoM959J5JG4Q0CI/I/mZ5I8/dnl859M3PvhRZi3HP4OAFhBg5oEyDoBcSlg9EDD+IErZKBgFo2AUjFgAAHtnQ3OIS2rjAAAAAElFTkSuQmCC","orcid":"","institution":"Beihang University","correspondingAuthor":true,"prefix":"","firstName":"Zheng","middleName":"","lastName":"Zheng","suffix":""}],"badges":[],"createdAt":"2024-06-29 16:23:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4660114/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4660114/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11219-025-09716-5","type":"published","date":"2025-03-31T15:57:57+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":80082062,"identity":"442cd069-ba36-4d6e-b7f0-9ea74595194f","added_by":"auto","created_at":"2025-04-07 16:06:32","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":713146,"visible":true,"origin":"","legend":"","description":"","filename":"20240702Evaluatingtheeffectivenessofneuroncoveragemetricsametamorphictestingapproach.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4660114/v1_covered_25ac07cd-fc9b-43d9-a96b-834939045c9e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Evaluating the effectiveness of neuron coverage metrics: a metamorphic-testing approach","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":"software-quality-journal","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sqjo","sideBox":"Learn more about [Software Quality Journal](http://link.springer.com/journal/11219)","snPcode":"11219","submissionUrl":"https://submission.nature.com/new-submission/11219/3","title":"Software Quality Journal","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"deep learning system, deep neural network, machine learning, metamorphic relation, metamorphic testing, neuron coverage","lastPublishedDoi":"10.21203/rs.3.rs-4660114/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4660114/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Deep neural networks (DNNs) are now widely used in many sectors of our society. This phenomenon also means that if these DNNs contain faults, they will have profound adverse impacts on our daily lives. Thus, DNNs have to be comprehensively tested for ''correctness'' before they are released for use.Since such testing involves the use of a DNN test set, the comprehensiveness of this test set is of utmost importance. Until now, many researchers have proposed their own neuron-coverage (NC) metrics to measure the comprehensiveness of a DNN test set. However, their studies solely focused on those DNN testing scenarios with the presence of a test oracle. We observed that, in reality, there are many DNN testing scenarios where a test oracle does not exist and, therefore, the results of all previous studies may be inapplicable to these testing scenarios.Inspired by this observation, we have performed an empirical study to investigate the usefulness of some common and major NC metrics in terms of correlation analysis and invariability analysis. Our experiment results showed that, on the one hand, some NC metrics are useful measures of DNN test-set comprehensiveness (in terms of correlation analysis), but on the other hand, these metrics are not robust enough (in terms of invariability analysis).","manuscriptTitle":"Evaluating the effectiveness of neuron coverage metrics: a metamorphic-testing approach","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-24 01:34:22","doi":"10.21203/rs.3.rs-4660114/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-10-20T13:19:34+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-10-18T11:52:55+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-08-31T13:31:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"41000755864437526815076298802359293292","date":"2024-08-07T22:18:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"195148243111136892252126606037528809273","date":"2024-08-05T15:45:19+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-08-05T15:38:59+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-07-02T03:50:27+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-07-02T03:49:35+00:00","index":"","fulltext":""},{"type":"submitted","content":"Software Quality Journal","date":"2024-06-29T16:21:19+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"software-quality-journal","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sqjo","sideBox":"Learn more about [Software Quality Journal](http://link.springer.com/journal/11219)","snPcode":"11219","submissionUrl":"https://submission.nature.com/new-submission/11219/3","title":"Software Quality Journal","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"9b1485c7-da1d-4f24-b10b-6e6846a0ad73","owner":[],"postedDate":"July 24th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-04-07T16:02:36+00:00","versionOfRecord":{"articleIdentity":"rs-4660114","link":"https://doi.org/10.1007/s11219-025-09716-5","journal":{"identity":"software-quality-journal","isVorOnly":false,"title":"Software Quality Journal"},"publishedOn":"2025-03-31 15:57:57","publishedOnDateReadable":"March 31st, 2025"},"versionCreatedAt":"2024-07-24 01:34:22","video":"","vorDoi":"10.1007/s11219-025-09716-5","vorDoiUrl":"https://doi.org/10.1007/s11219-025-09716-5","workflowStages":[]},"version":"v1","identity":"rs-4660114","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4660114","identity":"rs-4660114","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}