{"id":"https://openalex.org/W3091588759","doi":"https://doi.org/10.1145/3379597.3387501","title":"A C/C++ Code Vulnerability Dataset with Code Changes and CVE Summaries","display_name":"A C/C++ Code Vulnerability Dataset with Code Changes and CVE Summaries","publication_year":2020,"publication_date":"2020-06-29","ids":{"openalex":"https://openalex.org/W3091588759","doi":"https://doi.org/10.1145/3379597.3387501","mag":"3091588759"},"language":"en","primary_location":{"id":"doi:10.1145/3379597.3387501","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3379597.3387501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Mining Software Repositories","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101562161","display_name":"Jiahao Fan","orcid":"https://orcid.org/0000-0001-7668-5585"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiahao Fan","raw_affiliation_strings":["SPACE Lab, Informatics, New Jersey Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SPACE Lab, Informatics, New Jersey Institute of Technology","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107249192","display_name":"Yi Li","orcid":"https://orcid.org/0009-0007-0143-0677"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi Li","raw_affiliation_strings":["SPACE Lab, Informatics, New Jersey Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SPACE Lab, Informatics, New Jersey Institute of Technology","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070990953","display_name":"Shaohua Wang","orcid":"https://orcid.org/0000-0001-5777-7759"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shaohua Wang","raw_affiliation_strings":["SPACE Lab, Informatics, New Jersey Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SPACE Lab, Informatics, New Jersey Institute of Technology","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089000736","display_name":"Tien N. Nguyen","orcid":"https://orcid.org/0009-0006-7962-6090"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tien N. Nguyen","raw_affiliation_strings":["CS Department, The University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CS Department, The University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":450,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"508","last_page":"512"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11424","display_name":"Security and Verification in Computing","score":0.998199999332428,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9959999918937683,"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":0.7929444313049316},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.7262669205665588},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6750049591064453},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.6204113960266113},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.46494024991989136},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.44119542837142944},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4155789613723755},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.32798755168914795},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32160520553588867},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.22984585165977478},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.19638049602508545},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.14952495694160461},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12896806001663208}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7929444313049316},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.7262669205665588},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6750049591064453},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.6204113960266113},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.46494024991989136},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.44119542837142944},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4155789613723755},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32798755168914795},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32160520553588867},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.22984585165977478},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.19638049602508545},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.14952495694160461},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12896806001663208},{"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":1,"locations":[{"id":"doi:10.1145/3379597.3387501","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3379597.3387501","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Mining Software Repositories","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.44999998807907104}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1992114977","https://openalex.org/W2740329368","https://openalex.org/W2884642766","https://openalex.org/W2962698568","https://openalex.org/W2962960733","https://openalex.org/W2963321189","https://openalex.org/W2963926786"],"related_works":["https://openalex.org/W2377966044","https://openalex.org/W4213227643","https://openalex.org/W4385958754","https://openalex.org/W1569374677","https://openalex.org/W2464013388","https://openalex.org/W4302337289","https://openalex.org/W4285818718","https://openalex.org/W4250021107","https://openalex.org/W2002850079","https://openalex.org/W2527612534"],"abstract_inverted_index":{"We":[0,14,106],"collected":[1,31],"a":[2],"large":[3],"C/C++":[4],"code":[5,27,60,68,74,81,90,109,135],"vulnerability":[6,72,86,133],"dataset":[7],"from":[8,38,94],"open-source":[9],"Github":[10,59,96],"projects,":[11],"namely":[12],"Big-Vul.":[13],"crawled":[15],"the":[16,32,36,39,52,67,103,108,112,132],"public":[17],"Common":[18],"Vulnerabilities":[19],"and":[20,24,48,55,70,128],"Exposures":[21],"(CVE)":[22],"database":[23],"CVE-related":[25],"source":[26],"repositories.":[28],"Specifically,":[29],"we":[30,63],"descriptive":[33,114],"information":[34,54,99],"of":[35,66],"vulnerabilities":[37,82,91],"CVE":[40,43,45,49,53,113],"database,":[41],"e.g.,":[42,126],"IDs,":[44],"severity":[46],"scores,":[47],"summaries.":[50],"With":[51],"its":[56],"related":[57,73,134],"published":[58],"repository":[61],"links,":[62],"downloaded":[64],"all":[65],"repositories":[69],"extracted":[71,93],"changes.":[75,136],"In":[76],"total,":[77],"Big-Vul":[78,118,137],"contains":[79],"3,754":[80],"spanning":[83],"91":[84],"different":[85],"types.":[87],"All":[88,98],"these":[89],"are":[92],"348":[95],"projects.":[97],"is":[100,138],"stored":[101],"in":[102],"CSV":[104],"format.":[105],"linked":[107],"changes":[110],"with":[111],"information.":[115],"Thus,":[116],"our":[117],"can":[119],"be":[120],"used":[121],"for":[122],"various":[123],"research":[124],"topics,":[125],"detecting":[127],"fixing":[129],"vulnerabilities,":[130],"analyzing":[131],"publicly":[139],"available":[140],"on":[141],"Github.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":75},{"year":2025,"cited_by_count":161},{"year":2024,"cited_by_count":108},{"year":2023,"cited_by_count":62},{"year":2022,"cited_by_count":31},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-18T07:39:51.176621","created_date":"2025-10-10T00:00:00"}
