[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119900-en":3,"doc-seo-119900-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},119900,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",6,"Technology","FuSeBMC AI - Acceleration of Hybrid Approach through Machine Learning","FuSeBMC-AI is a test generation tool built on machine learning for configuring hybrid software verification. It extracts program features from the input C code and uses support vector machine and neural network models to predict an optimal hybrid configuration. Bounded Model Checking and fuzzing serve as back-end verification engines, guided by the predicted settings. The approach improves over the default configuration of the underlying engine in selected Test-Comp 2024 categories while reducing resource consumption.","The University of Manchester Research  \nFuSeBMC AI  \nLink to publication record in Manchester Research Explorer  \nCitation for published version (APA):  \nAlshmrany, K. M. , Aldughaim, M. , Wei, C. , Sweet, T. , Allmendinger, R. , & Cordeiro, L. C. (2024) . FuSeBMC AI: Acceleration of Hybrid Approach through Machine Learning.  \nCiting this paper  \nPlease note that where the full-text provided on Manchester Research Explorer is the Author Accepted Manuscript or Proof version this may differ from the final Published version. If citing, it is advised that you check and use the publisher's definitive version.  \nGeneral rights  \nCopyright and moral rights for the publications made accessible in the Research Explorer are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights.  \nTakedown policy  \nIf you believe that this document breaches copyright please refer to the University of Manchester’s Takedown Procedures [[http://man.ac.uk/04Y6Bo](http://man.ac.uk/04Y6Bo)] or contact [uml.scholarlycommunications@manchester.ac.uk](uml.scholarlycommunications@manchester.ac.uk) providing  \nrelevant details, so we can investigate your claim.  \nDownload date:09 . May. 2024  \n[ cs .CR] 9 Apr 2024  \nFuSeBMC AI: Acceleration of Hybrid Approach through Machine Learning  \n(Competition Contribution)  \nKaled M. Alshmrany(B) 1 ,2[0000−0002−5822−5435], Mohannad Aldughaim2 ,3[0000−0002−5822−5435], Chenfeng Wei2[0009−0008−0416−3006],  \nTom Sweet4 , Richard Allmendinger2 , and Lucas C. Cordeiro2[0000−0002−6235−4272]  \n1 Institute of Public Administration, Jeddah, Saudi Arabia  \n2 University of Manchester, Manchester, UK  \n3 King Saud University, Riyadh, Saudi Arabia  \n4 SES Escrow, Handforth Cheshire, UK  \n[shamranial@ipa.edu.sa](shamranial@ipa.edu.sa)  \nAbstract. We present FuSeBMC-AI, a test generation tool grounded in machine learning techniques. FuSeBMC-AI extracts various features from the program  \narXiv :2404 .06031v1  \nand employs support vector machine and neural network models to predict a hybrid approach’s optimal configuration. FuSeBMC-AI utilizes Bounded Model Checking and Fuzzing as back-end verification engines. FuSeBMC-AI outperforms the default configuration of the underlying verification engine in certain cases while concurrently diminishing resource consumption.  \n1 Test-Generation Approach  \nThe success of Machine Learning (ML) in automating diverse software engineering tasks is noteworthy, given the escalating complexity of modern software systems [1] . A hybrid approach of multiple techniques, including fuzzing, bounded model checking, and abstract interpretation, has proven effective in verifying software compliance with specified requirements [2] . However, challenges arise, particularly in software with intricate conditions or loops, where the primary obstacle lies in navigating the exponentially expanding program state space and managing resource consumption. Various efforts have been undertaken to enhance the hybrid approach, exemplified by initiatives such as FuSeBMC Interval Analysis [3] and Tracer [2] . FuSeBMC [4, 5] works as a test generator that synthesizes “smart seeds” with properties to enhance the efficiency of its hybrid fuzzer, achieving extensive coverage of programs. To address challenges related to program state explosion and resource usage, FuSeBMC provides the option of execution with diverse parameters (flags) . Unfortunately, determining the optimal flags for a specific program requires expert knowledge, often leading to the execution of hybrid tools with default settings and subsequent compromises in performance. This paper presents the FuSeBMC-AI tool to predict the optimal configuration flags for a given program. Specifically, FuSeBMC-AI employs ML models, support vector machines (SVMs), and neural network (NN) models to predict optimal settings. These ML models undergo training ","cbCaim9GO2cj7IiK","https://ap.wps.com/l/cbCaim9GO2cj7IiK","pdf",387774,1,"English","en",105,"# Abstract\n# Test-Generation Approach\n# Software Architecture\n## Setting Features\n## Dataset","[{\"question\":\"What problem does FuSeBMC-AI address in hybrid verification?\",\"answer\":\"It targets the difficulty of selecting optimal configuration flags, which otherwise often forces hybrid tools to run with default settings and compromise performance, especially under resource limits.\"},{\"question\":\"How does FuSeBMC-AI use machine learning to choose configuration flags?\",\"answer\":\"It extracts relevant features from the input C program, then trains SVM and neural network models to predict optimal configuration scores and recommended settings.\"},{\"question\":\"What verification engines does FuSeBMC-AI integrate?\",\"answer\":\"FuSeBMC-AI uses Bounded Model Checking and fuzzing as the back-end verification engines, applying the predicted hybrid configuration to execute the target program.\"}]","FuSeBMC AI - Acceleration of Hybrid Approach through Machine Learning | PDF",1785726903,15,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"fusebmc-ai-acceleration-of-hybrid-approach-through-machine-learning","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/technology/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/fusebmc-ai-acceleration-of-hybrid-approach-through-machine-learning/119900/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does FuSeBMC-AI address in hybrid verification?","Question",{"text":74,"@type":75},"It targets the difficulty of selecting optimal configuration flags, which otherwise often forces hybrid tools to run with default settings and compromise performance, especially under resource limits.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does FuSeBMC-AI use machine learning to choose configuration flags?",{"text":79,"@type":75},"It extracts relevant features from the input C program, then trains SVM and neural network models to predict optimal configuration scores and recommended settings.",{"name":81,"@type":72,"acceptedAnswer":82},"What verification engines does FuSeBMC-AI integrate?",{"text":83,"@type":75},"FuSeBMC-AI uses Bounded Model Checking and fuzzing as the back-end verification engines, applying the predicted hybrid configuration to execute the target program.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,112,117,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":110,"slug":111},50,"technology",{"id":113,"doc_module":4,"doc_module_name":45,"category_name":114,"show_sort_weight":115,"slug":116},7,"Healthcare",40,"healthcare",{"id":118,"doc_module":4,"doc_module_name":45,"category_name":119,"show_sort_weight":120,"slug":121},8,"Research & Report",30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]