Research on Citizen Privacy Risk Assessment Method Based on Retrieval-Augmented Generation

Research on Citizen Privacy Risk Assessment Method Based on Retrieval-Augmented Generation | 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 Research on Citizen Privacy Risk Assessment Method Based on Retrieval-Augmented Generation Jingye Qu, Fujian Luo This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9015963/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 16 You are reading this latest preprint version Abstract The issue of severe infringement on citizens' personal privacy makes it particularly crucial to assess the severity of personal information leaks. Current privacy risk assessment methods suffer from low evaluation efficiency and accuracy. To address these challenges, this paper proposes a research framework for privacy risk assessment based on Retrieval-Augmented Generation (RAG). First, we analyze privacy risk factors in cases of personal information infringement, construct an evaluation indicator system, and create a fine-tuned dataset and knowledge graph. Next, we propose a fine-tuning method dynamically adjusting the LoRA rank, which automatically contracts matrix dimensions by monitoring loss/gradient changes, reducing GPU memory consumption while maintaining generation quality. Finally, we introduce Retrieval-Augmented Generation (RAG), integrating internal knowledge from fine-tuned LLMs with weighted external evidence through joint reasoning to achieve more reliable judgments and privacy risk assessments. Compared to traditional approaches, this method demonstrates improved accuracy and text matching, validating its effectiveness. We propose a novel privacy risk assessment method based on Retrieval-Augmented Generation, mitigating the hallucination issues of large language models while enhancing the accuracy and efficiency of privacy risk evaluation tasks. Physical sciences/Engineering Physical sciences/Mathematics and computing Large language model Retrieval augmented generation Privacy risk assessment knowledge graph LoRA fine-tuning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 15 Apr, 2026 Reviewers agreed at journal 11 Apr, 2026 Reviews received at journal 06 Apr, 2026 Reviews received at journal 06 Apr, 2026 Reviewers agreed at journal 06 Apr, 2026 Reviews received at journal 06 Apr, 2026 Reviewers agreed at journal 06 Apr, 2026 Reviewers agreed at journal 06 Apr, 2026 Reviewers agreed at journal 06 Apr, 2026 Reviewers agreed at journal 05 Apr, 2026 Reviewers agreed at journal 05 Apr, 2026 Reviewers invited by journal 05 Apr, 2026 Editor invited by journal 25 Mar, 2026 Editor assigned by journal 04 Mar, 2026 Submission checks completed at journal 04 Mar, 2026 First submitted to journal 03 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-9015963","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":618329586,"identity":"f5dc2159-1a57-451e-a82c-ed64c28704c6","order_by":0,"name":"Jingye Qu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzklEQVRIiWNgGAWjYDACZhBhIGHHxsx8gCGBBC02yXzsbQlEaoGANMZ5PGcMiFNrzs787DFPwWFmNomczx8e7rBj4G/vxm+ZZTObueEMg8N8bBK52yQSzyQzSJw5uwGvFoPDDGYSHwxAtuRuY0hsYwYGRS4hLezfJBIMDjO2SeQ8/pDYVk+MFh6QLWmMbTxnGCQS2w4TpaVMcgYwkNnY28yAWo7zEPbL+ePbpHn+SNjJNzM//vizrVqOv70XvxYMwEOa8lEwCkbBKBgFWAEA77NAeGRmfhUAAAAASUVORK5CYII=","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Jingye","middleName":"","lastName":"Qu","suffix":""},{"id":618329588,"identity":"a4b0d809-5cfb-43e6-9cfe-e36fe60fab66","order_by":1,"name":"Fujian Luo","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Fujian","middleName":"","lastName":"Luo","suffix":""}],"badges":[],"createdAt":"2026-03-03 05:08:31","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9015963/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9015963/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106725656,"identity":"7a4b6165-b8c5-413b-b418-a43aec2db7cc","added_by":"auto","created_at":"2026-04-12 18:33:23","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":692071,"visible":true,"origin":"","legend":"","description":"","filename":"manuscriptforsubmissionstoscientificreports.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9015963/v1_covered_86472beb-ca1b-4e18-8821-c04341497dd0.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Research on Citizen Privacy Risk Assessment Method Based on Retrieval-Augmented Generation","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Large language model, Retrieval augmented generation, Privacy risk assessment, knowledge graph, LoRA fine-tuning","lastPublishedDoi":"10.21203/rs.3.rs-9015963/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9015963/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe issue of severe infringement on citizens' personal privacy makes it particularly crucial to assess the severity of personal information leaks. Current privacy risk assessment methods suffer from low evaluation efficiency and accuracy. To address these challenges, this paper proposes a research framework for privacy risk assessment based on Retrieval-Augmented Generation (RAG). First, we analyze privacy risk factors in cases of personal information infringement, construct an evaluation indicator system, and create a fine-tuned dataset and knowledge graph. Next, we propose a fine-tuning method dynamically adjusting the LoRA rank, which automatically contracts matrix dimensions by monitoring loss/gradient changes, reducing GPU memory consumption while maintaining generation quality. Finally, we introduce Retrieval-Augmented Generation (RAG), integrating internal knowledge from fine-tuned LLMs with weighted external evidence through joint reasoning to achieve more reliable judgments and privacy risk assessments. Compared to traditional approaches, this method demonstrates improved accuracy and text matching, validating its effectiveness. We propose a novel privacy risk assessment method based on Retrieval-Augmented Generation, mitigating the hallucination issues of large language models while enhancing the accuracy and efficiency of privacy risk evaluation tasks.\u003c/p\u003e","manuscriptTitle":"Research on Citizen Privacy Risk Assessment Method Based on Retrieval-Augmented Generation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-10 03:44:20","doi":"10.21203/rs.3.rs-9015963/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-15T07:02:34+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"34838928271576310563159747561498134790","date":"2026-04-11T10:20:56+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-06T15:01:53+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-06T10:39:20+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"241793833106479136620342938700387846389","date":"2026-04-06T10:33:15+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-06T05:11:51+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"173855493344773883678892245743058002500","date":"2026-04-06T05:02:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"101693541307252532046345870187495229290","date":"2026-04-06T04:59:20+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"257322755839007165917622770320857039453","date":"2026-04-06T04:26:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"113143349721928469477641562867750391312","date":"2026-04-06T02:27:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"3077952270368779331533888918974581032","date":"2026-04-06T02:07:22+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-06T01:46:20+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-03-25T05:08:44+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-04T06:49:27+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-04T06:45:52+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-03-03T05:03:59+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"08b94d5b-1d3b-46ec-82d4-60cd11b205c1","owner":[],"postedDate":"April 10th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":65796627,"name":"Physical sciences/Engineering"},{"id":65796628,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-04-22T01:23:33+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-10 03:44:20","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9015963","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9015963","identity":"rs-9015963","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}