{"id":"https://openalex.org/W4403413444","doi":"https://doi.org/10.1145/3674805.3686675","title":"Automatic Data Labeling for Software Vulnerability Prediction Models: How Far Are We?","display_name":"Automatic Data Labeling for Software Vulnerability Prediction Models: How Far Are We?","publication_year":2024,"publication_date":"2024-10-15","ids":{"openalex":"https://openalex.org/W4403413444","doi":"https://doi.org/10.1145/3674805.3686675"},"language":"en","primary_location":{"id":"doi:10.1145/3674805.3686675","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3674805.3686675","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3674805.3686675","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017801401","display_name":"Triet Huynh Minh Le","orcid":"https://orcid.org/0000-0003-1935-037X"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Triet Huynh Minh Le","raw_affiliation_strings":["CREST - the Centre for Research on Engineering Software Technologies, The University of Adelaide, Australia"],"raw_orcid":"https://orcid.org/0000-0003-1935-037X","affiliations":[{"raw_affiliation_string":"CREST - the Centre for Research on Engineering Software Technologies, The University of Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103075476","display_name":"Muhammad Ali Babar","orcid":"https://orcid.org/0000-0001-9696-3626"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Muhammad Ali Babar","raw_affiliation_strings":["CREST - the Centre for Research on Engineering Software Technologies, The University of Adelaide, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9696-3626","affiliations":[{"raw_affiliation_string":"CREST - the Centre for Research on Engineering Software Technologies, The University of Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5681781"],"apc_list":null,"apc_paid":null,"fwci":0.8447,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74596182,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"131","last_page":"142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9991000294685364,"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/T10260","display_name":"Software Engineering Research","score":0.9987999796867371,"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/T12127","display_name":"Software System Performance and Reliability","score":0.984499990940094,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7398170828819275},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5483067035675049},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.5267283916473389},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3452238440513611},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.13473308086395264},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10848826169967651}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7398170828819275},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5483067035675049},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.5267283916473389},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3452238440513611},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.13473308086395264},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10848826169967651}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3674805.3686675","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3674805.3686675","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3674805.3686675","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3674805.3686675","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1979290264","https://openalex.org/W1997646511","https://openalex.org/W2003315002","https://openalex.org/W2079753286","https://openalex.org/W2117539524","https://openalex.org/W2139885493","https://openalex.org/W2141861154","https://openalex.org/W2146649871","https://openalex.org/W2161336914","https://openalex.org/W2166336492","https://openalex.org/W2172232422","https://openalex.org/W2295598076","https://openalex.org/W2493916176","https://openalex.org/W2740329368","https://openalex.org/W2748690817","https://openalex.org/W2768348081","https://openalex.org/W2890264517","https://openalex.org/W2912500072","https://openalex.org/W2914747561","https://openalex.org/W2914851262","https://openalex.org/W2918408501","https://openalex.org/W2962698568","https://openalex.org/W2967556797","https://openalex.org/W2984772254","https://openalex.org/W3006127095","https://openalex.org/W3083954092","https://openalex.org/W3091102523","https://openalex.org/W3091588759","https://openalex.org/W3098605233","https://openalex.org/W3104128335","https://openalex.org/W3127782461","https://openalex.org/W3142656464","https://openalex.org/W3156669901","https://openalex.org/W3163206498","https://openalex.org/W3173121933","https://openalex.org/W3177116043","https://openalex.org/W3183469243","https://openalex.org/W3184339106","https://openalex.org/W3194346579","https://openalex.org/W3195612455","https://openalex.org/W3195703954","https://openalex.org/W3201862078","https://openalex.org/W3202871865","https://openalex.org/W4210443011","https://openalex.org/W4220908965","https://openalex.org/W4232648333","https://openalex.org/W4233410239","https://openalex.org/W4237088642","https://openalex.org/W4249033934","https://openalex.org/W4285490489","https://openalex.org/W4285821122","https://openalex.org/W4286331368","https://openalex.org/W4286979219","https://openalex.org/W4288048266","https://openalex.org/W4289976167","https://openalex.org/W4296483261","https://openalex.org/W4308643013","https://openalex.org/W4312436517","https://openalex.org/W4312439220","https://openalex.org/W4312690534","https://openalex.org/W4312969325","https://openalex.org/W4384345694","https://openalex.org/W4384345698"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032"],"abstract_inverted_index":{"Background:":[0],"Software":[1],"Vulnerability":[2],"(SV)":[3],"prediction":[4,49,123],"needs":[5],"large-sized":[6],"and":[7,24,57,62,78,112,135,142,154,183],"high-quality":[8],"data":[9,46,85,168,172],"to":[10,133,169],"perform":[11,131],"well.":[12],"Current":[13],"SV":[14,37,48,68,72,84,122,167,175,194],"datasets":[15],"mostly":[16],"require":[17],"expensive":[18],"labeling":[19,38],"efforts":[20,34],"by":[21],"experts":[22],"(human-labeled)":[23],"thus":[25],"are":[26,32,108],"limited":[27],"in":[28,35,90,138,165],"size.":[29],"Meanwhile,":[30],"there":[31],"growing":[33],"automatic":[36],"at":[39],"scale.":[40],"However,":[41],"the":[42,60,65,96,105,117,126,146,152,163,171,181,190],"fitness":[43],"of":[44,64,104,156,185],"auto-labeled":[45,67,97,106,128,166,187],"for":[47,71,94,160,174,192],"is":[50],"still":[51],"largely":[52],"unknown.":[53],"Aims:":[54],"We":[55,100,149],"quantitatively":[56],"qualitatively":[58],"study":[59,179],"quality":[61],"use":[63],"state-of-the-art":[66],"data,":[69],"D2A,":[70],"prediction.":[73,176,195],"Method:":[74],"Using":[75],"multiple":[76],"sources":[77],"manual":[79],"validation,":[80],"we":[81],"curate":[82],"clean":[83],"from":[86],"human-labeled":[87],"SV-fixing":[88],"commits":[89],"two":[91],"well-known":[92],"projects":[93],"investigating":[95],"counterparts.":[98],"Results:":[99],"discover":[101],"that":[102],"50+%":[103],"SVs":[107,129],"noisy":[109,127],"(incorrectly":[110],"labeled),":[111],"they":[113],"hardly":[114],"overlap":[115],"with":[116],"publicly":[118],"reported":[119],"ones.":[120],"Yet,":[121],"models":[124],"utilizing":[125],"can":[130],"up":[132],"22%":[134],"90%":[136],"better":[137],"Matthews":[139],"Correlation":[140],"Coefficient":[141],"Recall,":[143],"respectively,":[144],"than":[145],"original":[147],"models.":[148],"also":[150],"reveal":[151],"promises":[153],"difficulties":[155],"applying":[157],"noise-reduction":[158],"methods":[159],"automatically":[161],"addressing":[162],"noise":[164],"maximize":[170],"utilization":[173],"Conclusions:":[177],"Our":[178],"informs":[180],"benefits":[182],"challenges":[184],"using":[186],"SVs,":[188],"paving":[189],"way":[191],"large-scale":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}