{"id":"https://openalex.org/W2967556797","doi":"https://doi.org/10.1145/3338906.3338941","title":"The importance of accounting for real-world labelling when predicting software vulnerabilities","display_name":"The importance of accounting for real-world labelling when predicting software vulnerabilities","publication_year":2019,"publication_date":"2019-08-09","ids":{"openalex":"https://openalex.org/W2967556797","doi":"https://doi.org/10.1145/3338906.3338941","mag":"2967556797"},"language":"en","primary_location":{"id":"doi:10.1145/3338906.3338941","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3338906.3338941","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3338906.3338941","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3338906.3338941","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101828371","display_name":"Matthieu Jimenez","orcid":"https://orcid.org/0000-0003-4061-1108"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":true,"raw_author_name":"Matthieu Jimenez","raw_affiliation_strings":["University of Luxembourg, Luxembourg"],"affiliations":[{"raw_affiliation_string":"University of Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003103545","display_name":"Renaud Rwemalika","orcid":"https://orcid.org/0000-0003-2945-0286"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Renaud Rwemalika","raw_affiliation_strings":["University of Luxembourg, Luxembourg"],"affiliations":[{"raw_affiliation_string":"University of Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081145634","display_name":"Mike Papadakis","orcid":"https://orcid.org/0000-0003-1852-2547"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Mike Papadakis","raw_affiliation_strings":["University of Luxembourg, Luxembourg"],"affiliations":[{"raw_affiliation_string":"University of Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012165852","display_name":"Federica Sarro","orcid":"https://orcid.org/0000-0002-9146-442X"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Federica Sarro","raw_affiliation_strings":["University College London, UK"],"affiliations":[{"raw_affiliation_string":"University College London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040574362","display_name":"Yves Le Traon","orcid":"https://orcid.org/0000-0002-1045-4861"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Yves Le Traon","raw_affiliation_strings":["University of Luxembourg, Luxembourg"],"affiliations":[{"raw_affiliation_string":"University of Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000019783","display_name":"Mark Harman","orcid":"https://orcid.org/0000-0002-5864-4488"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]},{"id":"https://openalex.org/I4210111288","display_name":"Meta (United Kingdom)","ror":"https://ror.org/020ye1821","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210111288","https://openalex.org/I4210114444"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Harman","raw_affiliation_strings":["University College London, UK / Facebook, UK"],"affiliations":[{"raw_affiliation_string":"University College London, UK / Facebook, UK","institution_ids":["https://openalex.org/I4210111288","https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101828371"],"corresponding_institution_ids":["https://openalex.org/I186903577"],"apc_list":null,"apc_paid":null,"fwci":14.0916,"has_fulltext":true,"cited_by_count":70,"citation_normalized_percentile":{"value":0.98820997,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"695","last_page":"705"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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":1.0,"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":0.9994000196456909,"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":0.9937000274658203,"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/labelling","display_name":"Labelling","score":0.8480865955352783},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7227166295051575},{"id":"https://openalex.org/keywords/linux-kernel","display_name":"Linux kernel","score":0.6705183386802673},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.6686436533927917},{"id":"https://openalex.org/keywords/upgrade","display_name":"Upgrade","score":0.5987148284912109},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.5000371932983398},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.4930278956890106},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4735238552093506},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4687609374523163},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.45966681838035583},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38289764523506165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34366926550865173},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.29664331674575806},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1633114516735077},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.100269615650177},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08482760190963745}],"concepts":[{"id":"https://openalex.org/C2780523633","wikidata":"https://www.wikidata.org/wiki/Q380709","display_name":"Labelling","level":2,"score":0.8480865955352783},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7227166295051575},{"id":"https://openalex.org/C553261973","wikidata":"https://www.wikidata.org/wiki/Q14579","display_name":"Linux kernel","level":2,"score":0.6705183386802673},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.6686436533927917},{"id":"https://openalex.org/C2780615140","wikidata":"https://www.wikidata.org/wiki/Q920419","display_name":"Upgrade","level":2,"score":0.5987148284912109},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.5000371932983398},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.4930278956890106},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4735238552093506},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4687609374523163},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.45966681838035583},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38289764523506165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34366926550865173},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.29664331674575806},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1633114516735077},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.100269615650177},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08482760190963745},{"id":"https://openalex.org/C73484699","wikidata":"https://www.wikidata.org/wiki/Q161733","display_name":"Criminology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3338906.3338941","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3338906.3338941","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3338906.3338941","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10083408","is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10083408/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In: Dumas, M and Pfahl, D and Apel, S and Russo, A, (eds.) Proceedings of the 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2019).  (pp. pp. 695-705).  ACM (Association for Computing Machinery): New York, NY, USA. (2019)     ","raw_type":"Proceedings paper"},{"id":"pmh:oai:orbilu.uni.lu:10993/40076","is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/40076","pdf_url":null,"source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) (2019); 27th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE), from 26-8-2019 to 30-8-2019","raw_type":"peer reviewed"}],"best_oa_location":{"id":"doi:10.1145/3338906.3338941","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3338906.3338941","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3338906.3338941","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.44999998807907104,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2746349962","display_name":null,"funder_award_id":"C17/IS/11686509/CODEMATES","funder_id":"https://openalex.org/F4320321038","funder_display_name":"Fonds National de la Recherche Luxembourg"},{"id":"https://openalex.org/G3732689433","display_name":null,"funder_award_id":"741278 (EPIC: Evolutionary Program Improvement Collaborators).","funder_id":"https://openalex.org/F4320338352","funder_display_name":"FP7 Ideas: European Research Council"},{"id":"https://openalex.org/G381275068","display_name":null,"funder_award_id":"AFR PHD 11278802","funder_id":"https://openalex.org/F4320321038","funder_display_name":"Fonds National de la Recherche Luxembourg"}],"funders":[{"id":"https://openalex.org/F4320321038","display_name":"Fonds National de la Recherche Luxembourg","ror":"https://ror.org/039z13y21"},{"id":"https://openalex.org/F4320338352","display_name":"FP7 Ideas: European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2967556797.pdf","grobid_xml":"https://content.openalex.org/works/W2967556797.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W38372507","https://openalex.org/W149472151","https://openalex.org/W154870643","https://openalex.org/W165633843","https://openalex.org/W1997236144","https://openalex.org/W1997646511","https://openalex.org/W2004758929","https://openalex.org/W2015001165","https://openalex.org/W2022695357","https://openalex.org/W2043837581","https://openalex.org/W2055765785","https://openalex.org/W2067148378","https://openalex.org/W2070425304","https://openalex.org/W2079753286","https://openalex.org/W2106578314","https://openalex.org/W2109553965","https://openalex.org/W2118283821","https://openalex.org/W2119327016","https://openalex.org/W2148143831","https://openalex.org/W2151666086","https://openalex.org/W2154398797","https://openalex.org/W2161336914","https://openalex.org/W2166336492","https://openalex.org/W2170735442","https://openalex.org/W2244669237","https://openalex.org/W2344072768","https://openalex.org/W2348136092","https://openalex.org/W2367798545","https://openalex.org/W2471516951","https://openalex.org/W2517094600","https://openalex.org/W2521698904","https://openalex.org/W2559874352","https://openalex.org/W2623262941","https://openalex.org/W2753715782","https://openalex.org/W2795013017","https://openalex.org/W2804743641","https://openalex.org/W2810595416","https://openalex.org/W2889763677","https://openalex.org/W2896731104","https://openalex.org/W2900572580","https://openalex.org/W2900690747","https://openalex.org/W2969620576","https://openalex.org/W4252684946"],"related_works":["https://openalex.org/W2368672678","https://openalex.org/W1525479493","https://openalex.org/W2151725765","https://openalex.org/W2614013133","https://openalex.org/W4387321530","https://openalex.org/W3006186133","https://openalex.org/W2768753512","https://openalex.org/W2008085811","https://openalex.org/W3211835121","https://openalex.org/W4226208802"],"abstract_inverted_index":{"Previous":[0],"work":[1],"on":[2],"vulnerability":[3,64,163],"prediction":[4,65,98,164],"assume":[5],"that":[6,80],"predictive":[7,119,150],"models":[8],"are":[9,140],"trained":[10],"with":[11,70],"respect":[12],"to":[13,127,156,168],"perfect":[14],"labelling":[15,75,83,108],"information":[16],"(includes":[17],"labels":[18],"from":[19,31,122],"future,":[20],"as":[21],"yet":[22],"undiscovered":[23],"vulnerabilities).":[24],"In":[25],"this":[26],"paper":[27],"we":[28,102],"present":[29],"results":[30,78,99,139],"a":[32],"comprehensive":[33],"empirical":[34,160],"study":[35,56],"of":[36,44,60,118,149],"1,898":[37],"real-world":[38],"vulnerabilities":[39],"reported":[40],"in":[41,67,109],"74":[42],"releases":[43],"three":[45,61],"security-critical":[46],"open":[47],"source":[48],"systems":[49],"(Linux":[50],"Kernel,":[51,133],"OpenSSL":[52,134],"and":[53,71,96,125,135,146,159,166,171],"Wiresark).":[54],"Our":[55],"investigates":[57],"the":[58,73,81,89,110],"effectiveness":[59,120],"previously":[62],"proposed":[63],"approaches,":[66],"two":[68],"settings:":[69],"without":[72],"unrealistic":[74,82],"assumption.":[76],"The":[77,152],"reveal":[79],"assumption":[84],"can":[85],"profoundly":[86],"mis-":[87],"lead":[88],"scientific":[90,173],"conclusions":[91],"drawn;":[92],"suggesting":[93],"highly":[94],"effective":[95],"deployable":[97],"vanish":[100],"when":[101],"fully":[103],"account":[104],"for":[105,131,143,162],"realistically":[106],"available":[107],"experimental":[111,158],"methodology.":[112],"More":[113],"precisely,":[114],"MCC":[115],"mean":[116],"values":[117],"drop":[121],"0.77,":[123],"0.65":[124],"0.43":[126],"0.08,":[128],"0.22,":[129],"0.10":[130],"Linux":[132],"Wiresark,":[136],"respectively.":[137],"Similar":[138],"also":[141],"obtained":[142],"precision,":[144],"recall":[145],"other":[147],"assessments":[148],"efficacy.":[151],"community":[153],"therefore":[154],"needs":[155],"upgrade":[157],"methodology":[161],"evaluation":[165],"development":[167],"ensure":[169],"robust":[170],"actionable":[172],"findings.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}