Superior resilience to poisoning and amenability to unlearning in quantum machine learning

Superior resilience to poisoning and amenability to unlearning in quantum machine learning | 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 Superior resilience to poisoning and amenability to unlearning in quantum machine learning Yu-Qin Chen, shi-xin zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7352030/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 09 Mar, 2026 Read the published version in Nature Communications → Version 1 posted You are reading this latest preprint version Abstract The reliability of artificial intelligence hinges on the integrity of its training data, a foundation often compromised by noise and corruption. Here, through a comparative study of classical and quantum neural networks on both classical and quantum data, we reveal a fundamental difference in their response to data corruption. We find that classical models exhibit brittle memorization, leading to a failure in generalization. In contrast, quantum models demonstrate remarkable resilience, which is underscored by a phase transition-like response to increasing label noise, revealing a critical point beyond which the model’s performance changes qualitatively. We further establish and investigate the field of quantum machine unlearning, the process of efficiently forcing a trained model to forget corrupting influences. We show that the brittle nature of the classical model forms rigid, stubborn memories of erroneous data, making efficient unlearning challenging, while the quantum model is significantly more amenable to efficient forgetting with approximate unlearning methods. Our findings establish that quantum machine learning can possess a dual advantage of intrinsic resilience and efficient adaptability, providing a promising paradigm for the trustworthy and robust artificial intelligence of the future. Physical sciences/Physics/Quantum physics/Quantum information Physical sciences/Physics/Condensed-matter physics/Phase transitions and critical phenomena Full Text Additional Declarations There is NO Competing Interest. Supplementary Files sm.pdf Supplemental Information Cite Share Download PDF Status: Published Journal Publication published 09 Mar, 2026 Read the published version in Nature Communications → 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-7352030","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":513832024,"identity":"f4bb5eed-bc25-40ee-a6ba-84cee466d417","order_by":0,"name":"Yu-Qin Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1ElEQVRIiWNgGAWjYHACNiC2IV1LGulaDpOg3uB48rMHH3ect5vffvjh4wIGO3kG9rMH8Gs588zccOaZ28kbzqQZG89gSDZs4MlLwK/lRg6bNG/b7WQDCQYzaR4G5gQGCR4Dwlr+tp1Llp/B/v03D0M9kVoY2w7YMdzgMWPmYThMWIvkmWdmkr1tyQkGZ3KKpWcYHDds48nBr4UPGGISP9vs7OXbj2/8XFBRLc/Pfga/FoUDCWA6sQFIMDMYQKIJL5BvgGixZwBrGQWjYBSMglGABQAAr5ZAEdTCjSEAAAAASUVORK5CYII=","orcid":"","institution":"Graduate School of China Academy of Engineering Physics","correspondingAuthor":true,"prefix":"","firstName":"Yu-Qin","middleName":"","lastName":"Chen","suffix":""},{"id":513832025,"identity":"e30437b6-f8e7-4064-ad2a-a8a4f6a73735","order_by":1,"name":"shi-xin zhang","email":"","orcid":"","institution":"Institute of Physics, Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"shi-xin","middleName":"","lastName":"zhang","suffix":""}],"badges":[],"createdAt":"2025-08-12 06:30:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7352030/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7352030/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41467-026-70420-4","type":"published","date":"2026-03-09T04:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":107603977,"identity":"ff0c9a58-985b-4d1a-a324-160d020dac53","added_by":"auto","created_at":"2026-04-23 07:15:52","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":999747,"visible":true,"origin":"","legend":"Article File","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7352030/v1_covered_8ad66d3b-1458-41ac-ab31-3b97ce56af0d.pdf"},{"id":93476538,"identity":"2ff46935-d438-4446-9c84-215bc088b246","added_by":"auto","created_at":"2025-10-14 09:18:56","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":2327432,"visible":true,"origin":"","legend":"Supplemental Information","description":"","filename":"sm.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7352030/v1/99d42b54c0c3045132494ea7.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Superior resilience to poisoning and amenability to unlearning in quantum machine\nlearning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7352030/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7352030/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The reliability of artificial intelligence hinges on the integrity of its training data, a foundation\r\noften compromised by noise and corruption. Here, through a comparative study of classical and\r\nquantum neural networks on both classical and quantum data, we reveal a fundamental difference in\r\ntheir response to data corruption. We find that classical models exhibit brittle memorization, leading\r\nto a failure in generalization. In contrast, quantum models demonstrate remarkable resilience, which\r\nis underscored by a phase transition-like response to increasing label noise, revealing a critical point\r\nbeyond which the model’s performance changes qualitatively. We further establish and investigate\r\nthe field of quantum machine unlearning, the process of efficiently forcing a trained model to forget\r\ncorrupting influences. We show that the brittle nature of the classical model forms rigid, stubborn\r\nmemories of erroneous data, making efficient unlearning challenging, while the quantum model\r\nis significantly more amenable to efficient forgetting with approximate unlearning methods. Our\r\nfindings establish that quantum machine learning can possess a dual advantage of intrinsic resilience\r\nand efficient adaptability, providing a promising paradigm for the trustworthy and robust artificial\r\nintelligence of the future.","manuscriptTitle":"Superior resilience to poisoning and amenability to unlearning in quantum machine\nlearning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-14 09:18:51","doi":"10.21203/rs.3.rs-7352030/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"4c1be1a8-fb42-4276-aded-59e2d7664178","owner":[],"postedDate":"October 14th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":54591517,"name":"Physical sciences/Physics/Quantum physics/Quantum information"},{"id":54591518,"name":"Physical sciences/Physics/Condensed-matter physics/Phase transitions and critical phenomena"}],"tags":[],"updatedAt":"2026-04-23T07:15:43+00:00","versionOfRecord":{"articleIdentity":"rs-7352030","link":"https://doi.org/10.1038/s41467-026-70420-4","journal":{"identity":"nature-communications","isVorOnly":false,"title":"Nature Communications"},"publishedOn":"2026-03-09 04:00:00","publishedOnDateReadable":"March 9th, 2026"},"versionCreatedAt":"2025-10-14 09:18:51","video":"","vorDoi":"10.1038/s41467-026-70420-4","vorDoiUrl":"https://doi.org/10.1038/s41467-026-70420-4","workflowStages":[]},"version":"v1","identity":"rs-7352030","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7352030","identity":"rs-7352030","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}