{"id":"https://openalex.org/W4387298393","doi":"https://doi.org/10.1145/3607199.3607242","title":"DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detection","display_name":"DiverseVul: A New Vulnerable Source Code Dataset for Deep Learning Based Vulnerability Detection","publication_year":2023,"publication_date":"2023-10-03","ids":{"openalex":"https://openalex.org/W4387298393","doi":"https://doi.org/10.1145/3607199.3607242"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3607199.3607242","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3607199.3607242","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3607199.3607242","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064625106","display_name":"Yizheng Chen","orcid":"https://orcid.org/0000-0002-2019-5955"},"institutions":[],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yizheng Chen","raw_affiliation_strings":["University of Maryland, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Maryland, United States of America","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101871037","display_name":"Zhoujie Ding","orcid":"https://orcid.org/0009-0006-5467-2592"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"funder","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhoujie Ding","raw_affiliation_strings":["University of California, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092992234","display_name":"Lamya Alowain","orcid":"https://orcid.org/0009-0000-4207-2369"},"institutions":[{"id":"https://openalex.org/I1284598098","display_name":"King Abdulaziz City for Science and Technology","ror":"https://ror.org/05tdz6m39","country_code":"SA","type":"funder","lineage":["https://openalex.org/I1284598098"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Lamya Alowain","raw_affiliation_strings":["King Abdulaziz City for Science and Technology, Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"King Abdulaziz City for Science and Technology, Saudi Arabia","institution_ids":["https://openalex.org/I1284598098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077301505","display_name":"Xinyun Chen","orcid":"https://orcid.org/0000-0001-8379-902X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"funder","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinyun Chen","raw_affiliation_strings":["Google Deepmind, United States of America"],"affiliations":[{"raw_affiliation_string":"Google Deepmind, United States of America","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072545254","display_name":"David Wagner","orcid":"https://orcid.org/0000-0002-9944-9232"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"funder","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Wagner","raw_affiliation_strings":["University of California, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":38.987,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":50,"citation_normalized_percentile":{"value":0.999983,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"654","last_page":"668"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9996,"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":0.9996,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9984,"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"}},{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.998,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.7897227},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability","score":0.7175731},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6631819}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.7897227},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.75292575},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.7262889},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.7175731},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6631819},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40083435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3392611},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.29298574},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06340721},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3607199.3607242","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3607199.3607242","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2304.00409","pdf_url":"https://arxiv.org/pdf/2304.00409","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":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":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1145/3607199.3607242","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3607199.3607242","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":16,"referenced_works":["https://openalex.org/W1992114977","https://openalex.org/W2008626182","https://openalex.org/W2624697062","https://openalex.org/W2885030880","https://openalex.org/W2962960733","https://openalex.org/W3091588759","https://openalex.org/W3163206498","https://openalex.org/W3183469243","https://openalex.org/W3191226037","https://openalex.org/W3195703954","https://openalex.org/W4223953821","https://openalex.org/W4287673430","https://openalex.org/W4308731473","https://openalex.org/W4311165836","https://openalex.org/W4384345694","https://openalex.org/W4384345698"],"related_works":["https://openalex.org/W4393220254","https://openalex.org/W4390135167","https://openalex.org/W4321258516","https://openalex.org/W4317382653","https://openalex.org/W4287845917","https://openalex.org/W3156164993","https://openalex.org/W3081644756","https://openalex.org/W2385015894","https://openalex.org/W2171573941","https://openalex.org/W2051833850"],"abstract_inverted_index":{"We":[0,10],"propose":[1],"and":[2,22,39],"release":[3],"a":[4],"new":[5,30],"vulnerable":[6,34],"source":[7,23],"code":[8],"dataset.":[9],"curate":[11],"the":[12,26],"dataset":[13,31,48],"by":[14],"crawling":[15],"security":[16],"issue":[17],"websites,":[18],"extracting":[19],"vulnerability-fixing":[20],"commits":[21],"codes":[24],"from":[25,44],"corresponding":[27],"projects.":[28],"Our":[29,47],"contains":[32],"18,945":[33],"functions":[35,42],"spanning":[36],"150":[37],"CWEs":[38],"330,492":[40],"non-vulnerable":[41],"extracted":[43],"7,514":[45],"commits.":[46],"covers":[49],"295":[50],"more":[51],"projects":[52],"than":[53],"all":[54],"previous":[55],"datasets":[56],"combined.":[57]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4387298393","counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":36},{"year":2023,"cited_by_count":9}],"updated_date":"2025-02-20T11:52:38.098030","created_date":"2023-10-04"}