{"id":"https://openalex.org/W4312640079","doi":"https://doi.org/10.1145/3524842.3528446","title":"Noisy label learning for security defects","display_name":"Noisy label learning for security defects","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4312640079","doi":"https://doi.org/10.1145/3524842.3528446"},"language":"en","primary_location":{"id":"doi:10.1145/3524842.3528446","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524842.3528446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th 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/A5040400519","display_name":"Roland Croft","orcid":"https://orcid.org/0000-0001-5011-6587"},"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":"Roland Croft","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058693284","display_name":"Muhammad Ali Babar","orcid":"https://orcid.org/0000-0001-6653-6076"},"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":"M. Ali Babar","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101987301","display_name":"Huaming Chen","orcid":"https://orcid.org/0000-0001-5678-472X"},"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":"Huaming Chen","raw_affiliation_strings":["The University of Adelaide, Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Adelaide, 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":3.5174,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.94395103,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"435","last_page":"447"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9988999962806702,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.814651608467102},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7548143863677979},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7539598345756531},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.67369544506073},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5949344635009766},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.56136155128479},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.506142795085907},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.478588342666626},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.43434157967567444},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.42768803238868713},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.42273595929145813},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.34996676445007324},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.13863784074783325}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.814651608467102},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7548143863677979},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7539598345756531},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.67369544506073},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5949344635009766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.56136155128479},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.506142795085907},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.478588342666626},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.43434157967567444},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.42768803238868713},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.42273595929145813},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.34996676445007324},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.13863784074783325},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3524842.3528446","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3524842.3528446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th International Conference on Mining Software Repositories","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W54655540","https://openalex.org/W154870643","https://openalex.org/W1988019447","https://openalex.org/W2031648200","https://openalex.org/W2041282815","https://openalex.org/W2048117173","https://openalex.org/W2067691588","https://openalex.org/W2093897789","https://openalex.org/W2105672266","https://openalex.org/W2123958887","https://openalex.org/W2148143831","https://openalex.org/W2151666086","https://openalex.org/W2152575748","https://openalex.org/W2154398797","https://openalex.org/W2161336914","https://openalex.org/W2172232422","https://openalex.org/W2187089797","https://openalex.org/W2408181256","https://openalex.org/W2517094600","https://openalex.org/W2521698904","https://openalex.org/W2748690817","https://openalex.org/W2766521509","https://openalex.org/W2808113972","https://openalex.org/W2891244534","https://openalex.org/W2899867782","https://openalex.org/W2900872689","https://openalex.org/W2914747561","https://openalex.org/W2953653569","https://openalex.org/W2967556797","https://openalex.org/W2981328759","https://openalex.org/W2984772254","https://openalex.org/W2988966271","https://openalex.org/W3033777149","https://openalex.org/W3091588759","https://openalex.org/W3093673957","https://openalex.org/W3102035217","https://openalex.org/W3141989311","https://openalex.org/W3156669901","https://openalex.org/W3160070616","https://openalex.org/W3163206498","https://openalex.org/W3164087770","https://openalex.org/W3174937647","https://openalex.org/W3177116043","https://openalex.org/W3194346579","https://openalex.org/W3195213890","https://openalex.org/W3195612455","https://openalex.org/W3202359992","https://openalex.org/W4206600618","https://openalex.org/W4210493608","https://openalex.org/W4234552385","https://openalex.org/W4243379839","https://openalex.org/W4249033934","https://openalex.org/W4287673430","https://openalex.org/W4287751558","https://openalex.org/W6958604475"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W3108403339","https://openalex.org/W2162712524","https://openalex.org/W4287867034","https://openalex.org/W2175872006","https://openalex.org/W3005783148","https://openalex.org/W3021143552","https://openalex.org/W2004821155"],"abstract_inverted_index":{"Data-driven":[0],"software":[1,109,179],"engineering":[2],"processes,":[3],"such":[4],"as":[5,49],"vulnerability":[6,110],"prediction":[7],"heavily":[8],"rely":[9],"on":[10,120],"the":[11,14,36,39,54,67,91,127,161,165],"quality":[12],"of":[13,135,151,160],"data":[15],"used.":[16],"In":[17],"this":[18,75],"paper,":[19],"we":[20,77,113,145],"observe":[21],"that":[22,82,169],"it":[23],"is":[24],"infeasible":[25],"to":[26,44,85,108,123,139],"obtain":[27],"a":[28,115,153],"noise-free":[29],"security":[30,181],"defect":[31],"dataset":[32],"in":[33,61,66,149],"practice.":[34],"Despite":[35],"vulnerable":[37],"class,":[38],"non-vulnerable":[40],"modules":[41],"are":[42,83],"difficult":[43],"be":[45,175],"verified":[46],"and":[47,69,88,125,133,141,180],"determined":[48],"truly":[50],"exploit":[51],"free":[52],"given":[53],"limited":[55,94],"manual":[56],"efforts":[57],"available.":[58],"It":[59],"results":[60,167],"uncertainty,":[62],"introduces":[63],"labeling":[64],"noise":[65,121],"datasets":[68],"affects":[70],"conclusion":[71],"validity.":[72],"To":[73],"address":[74],"issue,":[76],"propose":[78,114],"novel":[79],"learning":[80,105,117,170],"methods":[81,106],"robust":[84],"label":[86,95,98,104,162],"impurities":[87],"can":[89,174],"leverage":[90],"most":[92],"from":[93,171],"data;":[96],"noisy":[97,103,128,172],"learning.":[99],"We":[100],"investigate":[101],"various":[102],"applied":[107],"prediction.":[111],"Specifically,":[112],"two-stage":[116],"method":[118],"based":[119],"cleaning":[122],"identify":[124],"remediate":[126],"samples,":[129],"which":[130],"improves":[131],"AUC":[132],"recall":[134],"baselines":[136],"by":[137],"up":[138],"8.9%":[140],"23.4%,":[142],"respectively.":[143],"Moreover,":[144],"discuss":[146],"several":[147],"hurdles":[148],"terms":[150],"achieving":[152],"performance":[154],"upper":[155],"bound":[156],"with":[157],"semi-omniscient":[158],"knowledge":[159],"noise.":[163],"Overall,":[164],"experimental":[166],"show":[168],"labels":[173],"effective":[176],"for":[177],"data-driven":[178],"analytics.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}