{"id":"https://openalex.org/W4399837262","doi":"https://doi.org/10.1145/3643991.3644886","title":"MegaVul: A C/C++ Vulnerability Dataset with Comprehensive Code Representations","display_name":"MegaVul: A C/C++ Vulnerability Dataset with Comprehensive Code Representations","publication_year":2024,"publication_date":"2024-04-15","ids":{"openalex":"https://openalex.org/W4399837262","doi":"https://doi.org/10.1145/3643991.3644886"},"language":"en","primary_location":{"id":"doi:10.1145/3643991.3644886","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3643991.3644886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Mining Software Repositories","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.12415","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102737361","display_name":"Chao Ni","orcid":"https://orcid.org/0000-0002-2906-0598"},"institutions":[{"id":"https://openalex.org/I137867983","display_name":"Central University of Finance and Economics","ror":"https://ror.org/008e3hf02","country_code":"CN","type":"education","lineage":["https://openalex.org/I137867983"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chao Ni","raw_affiliation_strings":["Zhejiang University, Hangzhou, China","Central University of Finance and Economics Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2906-0598","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Central University of Finance and Economics Beijing, China","institution_ids":["https://openalex.org/I137867983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028848423","display_name":"Liyu Shen","orcid":"https://orcid.org/0009-0002-3396-8766"},"institutions":[{"id":"https://openalex.org/I137867983","display_name":"Central University of Finance and Economics","ror":"https://ror.org/008e3hf02","country_code":"CN","type":"education","lineage":["https://openalex.org/I137867983"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liyu Shen","raw_affiliation_strings":["School of Software Technology, Zhejiang University, Hangzhou, China","Central University of Finance and Economics Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-3396-8766","affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Central University of Finance and Economics Beijing, China","institution_ids":["https://openalex.org/I137867983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101577570","display_name":"Xiaohu Yang","orcid":"https://orcid.org/0000-0003-4111-4189"},"institutions":[{"id":"https://openalex.org/I137867983","display_name":"Central University of Finance and Economics","ror":"https://ror.org/008e3hf02","country_code":"CN","type":"education","lineage":["https://openalex.org/I137867983"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohu Yang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China","Central University of Finance and Economics Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4111-4189","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Central University of Finance and Economics Beijing, China","institution_ids":["https://openalex.org/I137867983"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062548745","display_name":"Zhu Yan","orcid":"https://orcid.org/0009-0009-8817-3785"},"institutions":[{"id":"https://openalex.org/I137867983","display_name":"Central University of Finance and Economics","ror":"https://ror.org/008e3hf02","country_code":"CN","type":"education","lineage":["https://openalex.org/I137867983"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zhu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China","Central University of Finance and Economics Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-8817-3785","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Central University of Finance and Economics Beijing, China","institution_ids":["https://openalex.org/I137867983"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070990953","display_name":"Shaohua Wang","orcid":"https://orcid.org/0000-0001-5777-7759"},"institutions":[{"id":"https://openalex.org/I137867983","display_name":"Central University of Finance and Economics","ror":"https://ror.org/008e3hf02","country_code":"CN","type":"education","lineage":["https://openalex.org/I137867983"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohua Wang","raw_affiliation_strings":["Central University of Finance and Economics, Hangzhou, China","Zhejiang University Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5777-7759","affiliations":[{"raw_affiliation_string":"Central University of Finance and Economics, Hangzhou, China","institution_ids":["https://openalex.org/I137867983"]},{"raw_affiliation_string":"Zhejiang University Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102737361"],"corresponding_institution_ids":["https://openalex.org/I137867983","https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":5.0142,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.95767503,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"738","last_page":"742"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11424","display_name":"Security and Verification in Computing","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11424","display_name":"Security and Verification in Computing","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6851692795753479},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.5985172986984253},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5946561098098755},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2775273025035858},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.18800827860832214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6851692795753479},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.5985172986984253},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5946561098098755},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2775273025035858},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.18800827860832214},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3643991.3644886","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3643991.3644886","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st International Conference on Mining Software Repositories","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2406.12415","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.12415","pdf_url":"https://arxiv.org/pdf/2406.12415","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2406.12415","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.12415","pdf_url":"https://arxiv.org/pdf/2406.12415","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3041480715","display_name":null,"funder_award_id":"2022J184","funder_id":"https://openalex.org/F4320332587","funder_display_name":"Natural Science Foundation of Ningbo"},{"id":"https://openalex.org/G5088726832","display_name":null,"funder_award_id":"62202419","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320332587","display_name":"Natural Science Foundation of Ningbo","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4399837262.pdf"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W2144344516","https://openalex.org/W2565690877","https://openalex.org/W2781491433","https://openalex.org/W2900690747","https://openalex.org/W2913954081","https://openalex.org/W3091588759","https://openalex.org/W3101228802","https://openalex.org/W3127736190","https://openalex.org/W3177116043","https://openalex.org/W3183469243","https://openalex.org/W3194346579","https://openalex.org/W4287673430","https://openalex.org/W4384345641","https://openalex.org/W4389161980"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"We":[0,49],"constructed":[1],"a":[2,96],"newly":[3],"large-scale":[4],"and":[5,17,21,39,59,105,126],"comprehensive":[6],"C/C++":[7],"vulnerability":[8,81,107],"dataset":[9],"named":[10],"MegaVul":[11,69,91,120],"by":[12],"crawling":[13],"the":[14,33,36,55,61,114],"Common":[15],"Vulnerabilities":[16],"Exposures":[18],"(CVE)":[19],"database":[20,38],"CVE-related":[22],"open-source":[23,76],"projects.":[24],"Specifically,":[25],"we":[26],"collected":[27,73],"all":[28,41],"crawlable":[29],"descriptive":[30],"information":[31,110],"of":[32,98],"vulnerabilities":[34,72,104],"from":[35,45,74,84],"CVE":[37],"extracted":[40,56],"vulnerability-related":[42],"code":[43,57,62],"changes":[44],"28":[46],"Git-based":[47],"websites.":[48],"adopt":[50],"advanced":[51],"tools":[52],"to":[53,87,136],"ensure":[54],"integrality":[58],"enrich":[60],"with":[63],"four":[64],"different":[65,80],"transformed":[66],"representations.":[67],"Totally,":[68],"contains":[70],"17,380":[71],"992":[75],"repositories":[77],"spanning":[78],"169":[79],"types":[82],"disclosed":[83],"January":[85],"2006":[86],"October":[88],"2023.":[89],"Thus,":[90],"can":[92,132],"be":[93,128,133],"used":[94],"for":[95,117],"variety":[97],"software":[99],"security-related":[100],"tasks":[101],"including":[102],"detecting":[103],"assessing":[106],"severity.":[108],"All":[109],"is":[111,121],"stored":[112],"in":[113],"JSON":[115],"format":[116],"easy":[118],"usage.":[119],"publicly":[122],"available":[123],"on":[124],"GitHub":[125],"will":[127],"continuously":[129],"updated.":[130],"It":[131],"easily":[134],"extended":[135],"other":[137],"programming":[138],"languages.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":10}],"updated_date":"2026-05-27T09:02:27.158192","created_date":"2024-06-20T00:00:00"}
