LLM-based program analysis for source codes, abstract syntax trees and WebAssembly instructions

preprint OA: closed
Full text JSON View at publisher

Abstract

Abstract The advancement of Web3.0 technology has brought about an urgent need for ensuring the safety and reliability of the software systems. Program analysis, a crucial aspect of software security research needs a unified solution for various cross-language program. Moreover, the previous studies regard the necessity of capturing structured features from the ASTs, commonly holding a conception that plain text and compiled binary instructions were challenging to represent and identify. This paper proposes a method of program instruction file embedding directly into natural language. we train large language models (LLMs) with 20 billion to identify defect and non-defect of WebAssembly. Experiment results demonstrate that program instruction analysis surpasses traditional techniques, achieving state-of-the-art accuracy exceeding 98.1 percent. Our study also suggests a practical approach of plain text embedding using a 7.65 billion parameters language model. Interestingly, misformatted source cdoes are readable to humans but un-compilable, and the accuracy remains above 98.63 percent. This paper not only introduces novel instruction and plain text embedding approach for future program security analysis, but also provides new insights for subsequent research about the three program analysis forms of plain text, ASTs, and instructions.
Full text 14,289 characters · extracted from preprint-html · click to expand
LLM-based program analysis for source codes, abstract syntax trees and WebAssembly instructions | 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 LLM-based program analysis for source codes, abstract syntax trees and WebAssembly instructions Liangjun Deng, Qi Zhong, Yao Qiu, Jingxue Chen, Hang Lei, Shunkun Yang, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5419799/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract The advancement of Web3.0 technology has brought about an urgent need for ensuring the safety and reliability of the software systems. Program analysis, a crucial aspect of software security research needs a unified solution for various cross-language program. Moreover, the previous studies regard the necessity of capturing structured features from the ASTs, commonly holding a conception that plain text and compiled binary instructions were challenging to represent and identify. This paper proposes a method of program instruction file embedding directly into natural language. we train large language models (LLMs) with 20 billion to identify defect and non-defect of WebAssembly. Experiment results demonstrate that program instruction analysis surpasses traditional techniques, achieving state-of-the-art accuracy exceeding 98.1 percent. Our study also suggests a practical approach of plain text embedding using a 7.65 billion parameters language model. Interestingly, misformatted source cdoes are readable to humans but un-compilable, and the accuracy remains above 98.63 percent. This paper not only introduces novel instruction and plain text embedding approach for future program security analysis, but also provides new insights for subsequent research about the three program analysis forms of plain text, ASTs, and instructions. Blockchain group key agreement webassembly program analysis Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 24 Feb, 2025 Reviews received at journal 23 Nov, 2024 Reviews received at journal 20 Nov, 2024 Reviewers agreed at journal 19 Nov, 2024 Reviews received at journal 19 Nov, 2024 Reviewers agreed at journal 19 Nov, 2024 Reviewers agreed at journal 19 Nov, 2024 Reviewers invited by journal 19 Nov, 2024 Editor assigned by journal 17 Nov, 2024 Submission checks completed at journal 14 Nov, 2024 First submitted to journal 08 Nov, 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-5419799","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":381831411,"identity":"cba2eead-2f9d-4801-9aad-799637eabc22","order_by":0,"name":"Liangjun Deng","email":"","orcid":"","institution":"University of Electronic Science and Technology of China","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Liangjun","middleName":"","lastName":"Deng","suffix":""},{"id":381831412,"identity":"7596fc48-aa0f-4b71-b0a7-fe043654e1bb","order_by":1,"name":"Qi Zhong","email":"","orcid":"","institution":"University of Electronic Science and Technology of China","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Qi","middleName":"","lastName":"Zhong","suffix":""},{"id":381831413,"identity":"e48e3f21-3450-46d4-965d-6839498ed834","order_by":2,"name":"Yao Qiu","email":"","orcid":"","institution":"University of Electronic Science and Technology of China","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Yao","middleName":"","lastName":"Qiu","suffix":""},{"id":381831414,"identity":"d84bfc9b-de49-47a9-8523-f964aca24abf","order_by":3,"name":"Jingxue Chen","email":"","orcid":"","institution":"University of Electronic Science and Technology of China","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jingxue","middleName":"","lastName":"Chen","suffix":""},{"id":381831415,"identity":"2b622721-35c1-48ea-ba31-6a2b61a0c3ea","order_by":4,"name":"Hang Lei","email":"","orcid":"","institution":"University of Electronic Science and Technology of China","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Hang","middleName":"","lastName":"Lei","suffix":""},{"id":381831416,"identity":"75881216-24d3-4c0f-8cbb-757a9b53c8da","order_by":5,"name":"Shunkun Yang","email":"","orcid":"","institution":"University of Electronic Science and Technology of China","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Shunkun","middleName":"","lastName":"Yang","suffix":""},{"id":381831417,"identity":"d06c7aad-9176-4f92-bae1-c5a93c0586bf","order_by":6,"name":"Liming Zhou","email":"","orcid":"","institution":"University of Electronic Science and Technology of China","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Liming","middleName":"","lastName":"Zhou","suffix":""},{"id":381831418,"identity":"34029373-692a-497b-8737-0c7bda1931bf","order_by":7,"name":"Hongyuan Cheng","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+0lEQVRIiWNgGAWjYDACCSBmbIDxKizggsRqOSNBqhbGNiK08M9uPvbw6w6bPPmIHMPPhfMkEjccYD54m4fBLg+nJXeOpRvLnkkrNryRYyw9cxtIC1uyNQ9DcjEuLQYSOWbSkm2HEzfOyDGQ5gVr4TGT5mE4kNiAU0v+N5gW49+8c0Ba+L8R0JLDJvkRqGU+yDreBrAtbHi1SNxIM5NmbEtL3MDzrMya55iE8czDbMaWcwyScWrhn5H8TPJnm03i/Pbkzbd5amxk+443P7zxpsIOpxYQYOYBufBCApjj2MAMdjAe9UDA+ANIyPcfAHPs8asdBaNgFIyCkQgAY5pXWSC/dLsAAAAASUVORK5CYII=","orcid":"","institution":"University of Electronic Science and Technology of China","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Hongyuan","middleName":"","lastName":"Cheng","suffix":""}],"badges":[],"createdAt":"2024-11-09 05:08:05","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5419799/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5419799/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":71256187,"identity":"59727e15-ae5d-4605-84a0-d17b40ba3c15","added_by":"auto","created_at":"2024-12-12 15:28:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":802040,"visible":true,"origin":"","legend":"","description":"","filename":"LLMbasedprogramanalysisforsourcecodesabstractsyntaxtreesandWebAssemblyinstructions.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5419799/v1_covered_7a88e287-a9f7-4f2f-9920-f45256800c8d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"LLM-based program analysis for source codes, abstract syntax trees and WebAssembly instructions","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":"cluster-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Cluster Computing](https://www.springer.com/journal/10586)","snPcode":"10586","submissionUrl":"https://submission.nature.com/new-submission/10586/3","title":"Cluster Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Blockchain, group key agreement, webassembly, program analysis","lastPublishedDoi":"10.21203/rs.3.rs-5419799/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5419799/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe advancement of Web3.0 technology has brought about an urgent need for ensuring the safety and reliability of the software systems. Program analysis, a crucial aspect of software security research needs a unified solution for various cross-language program. Moreover, the previous studies regard the necessity of capturing structured features from the ASTs, commonly holding a conception that plain text and compiled binary instructions were challenging to represent and identify. This paper proposes a method of program instruction file embedding directly into natural language. we train large language models (LLMs) with 20\u0026nbsp;billion to identify defect and non-defect of WebAssembly. Experiment results demonstrate that program instruction analysis surpasses traditional techniques, achieving state-of-the-art accuracy exceeding 98.1 percent. Our study also suggests a practical approach of plain text embedding using a 7.65\u0026nbsp;billion parameters language model. Interestingly, misformatted source cdoes are readable to humans but un-compilable, and the accuracy remains above 98.63 percent. This paper not only introduces novel instruction and plain text embedding approach for future program security analysis, but also provides new insights for subsequent research about the three program analysis forms of plain text, ASTs, and instructions.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e","manuscriptTitle":"LLM-based program analysis for source codes, abstract syntax trees and WebAssembly instructions","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-12 15:20:36","doi":"10.21203/rs.3.rs-5419799/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-02-24T22:44:08+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-24T03:32:46+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-20T14:12:11+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"118350698489331695828901617990318551136","date":"2024-11-20T02:35:15+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-19T11:48:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"329080350004031158741829992630923160046","date":"2024-11-19T10:58:15+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"94641997614552995486246238162518585063","date":"2024-11-19T10:31:55+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-11-19T10:18:38+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-11-17T05:09:07+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-11-14T09:56:51+00:00","index":"","fulltext":""},{"type":"submitted","content":"Cluster Computing","date":"2024-11-09T04:54:18+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"cluster-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Cluster Computing](https://www.springer.com/journal/10586)","snPcode":"10586","submissionUrl":"https://submission.nature.com/new-submission/10586/3","title":"Cluster Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"04b70f7e-bda2-4e97-86af-2930e83687f3","owner":[],"postedDate":"December 12th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-06-02T23:38:18+00:00","versionOfRecord":[],"versionCreatedAt":"2024-12-12 15:20:36","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5419799","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5419799","identity":"rs-5419799","version":["v1"]},"buildId":"ApUGefWb6u5IBVtyqm6d5","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 (2024) — 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