{"id":"https://openalex.org/W4399667873","doi":"https://doi.org/10.1145/3661167.3661281","title":"Software Vulnerability Prediction in Low-Resource Languages: An Empirical Study of CodeBERT and ChatGPT","display_name":"Software Vulnerability Prediction in Low-Resource Languages: An Empirical Study of CodeBERT and ChatGPT","publication_year":2024,"publication_date":"2024-06-14","ids":{"openalex":"https://openalex.org/W4399667873","doi":"https://doi.org/10.1145/3661167.3661281"},"language":"en","primary_location":{"id":"doi:10.1145/3661167.3661281","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3661167.3661281","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 28th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3661167.3661281","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":"middle","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":"M. 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"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5095941300","display_name":"Tung Hoang Thai","orcid":"https://orcid.org/0009-0007-4957-5330"},"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":"Tung Hoang Thai","raw_affiliation_strings":["CREST - The Centre for Research on Engineering Software Technologies, The University of Adelaide, Australia"],"raw_orcid":"https://orcid.org/0009-0007-4957-5330","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":3.0974,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.9339207,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"679","last_page":"685"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9976000189781189,"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":0.9751999974250793,"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":0.6791387796401978},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.6489083766937256},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.48827266693115234},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4606073200702667},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.4170764982700348},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3439132571220398},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3162016272544861},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.23773542046546936},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13313958048820496},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11519166827201843}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6791387796401978},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.6489083766937256},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.48827266693115234},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4606073200702667},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.4170764982700348},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3439132571220398},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3162016272544861},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.23773542046546936},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13313958048820496},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11519166827201843},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3661167.3661281","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3661167.3661281","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 28th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3661167.3661281","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3661167.3661281","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 28th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W639218804","https://openalex.org/W2141861154","https://openalex.org/W2914747561","https://openalex.org/W2955991060","https://openalex.org/W3033777149","https://openalex.org/W3091588759","https://openalex.org/W3126095862","https://openalex.org/W3127782461","https://openalex.org/W3156556445","https://openalex.org/W3177116043","https://openalex.org/W3183469243","https://openalex.org/W3184339106","https://openalex.org/W3193639695","https://openalex.org/W3194346579","https://openalex.org/W3195612455","https://openalex.org/W3199693282","https://openalex.org/W4210443011","https://openalex.org/W4308641648","https://openalex.org/W4312436517","https://openalex.org/W4312439220","https://openalex.org/W4312969325","https://openalex.org/W4384345694","https://openalex.org/W4384345698","https://openalex.org/W4385187279","https://openalex.org/W4385187421","https://openalex.org/W4385249313"],"related_works":["https://openalex.org/W2095999892","https://openalex.org/W2018764758","https://openalex.org/W2383689843","https://openalex.org/W1550668881","https://openalex.org/W617913288","https://openalex.org/W2319323865","https://openalex.org/W2951745010","https://openalex.org/W2347958299","https://openalex.org/W2963125730","https://openalex.org/W2753096400"],"abstract_inverted_index":{"Background:":[0],"Software":[1],"Vulnerability":[2],"(SV)":[3],"prediction":[4,29,52,84,104,130],"in":[5,15,45,85,109,118,133,199],"emerging":[6,46],"languages":[7,20,47,88],"is":[8],"increasingly":[9],"important":[10],"to":[11,37,58,114,149,163,171],"ensure":[12],"software":[13],"security":[14],"modern":[16],"systems.":[17],"However,":[18],"these":[19],"usually":[21],"have":[22,179],"limited":[23],"SV":[24,42,51,83,103,129,191],"data":[25,43,76,141,145],"for":[26,79,101,165,173,189,196],"developing":[27],"high-performing":[28],"models.":[30],"Aims:":[31],"We":[32,63,94,178],"conduct":[33],"an":[34],"empirical":[35],"study":[36],"evaluate":[38],"the":[39,49,60,67,97,115,137,166,174,181,185,194],"impact":[40,139],"of":[41,99,125,140],"scarcity":[44],"on":[48,71],"state-of-the-art":[50,68],"model":[53,69],"and":[54,65,74,81,92,127,169,183],"investigate":[55],"potential":[56],"solutions":[57],"enhance":[59],"performance.":[61],"Method:":[62],"train":[64],"test":[66],"based":[70],"CodeBERT":[72],"with":[73,120],"without":[75],"sampling":[77,146],"techniques":[78,147],"function-level":[80,126],"line-level":[82,128],"three":[86],"low-resource":[87,102,134,190],"\u2013":[89],"Kotlin,":[90],"Swift,":[91],"Rust.":[93],"also":[95],"assess":[96],"effectiveness":[98],"ChatGPT":[100,153],"given":[105],"its":[106],"recent":[107],"success":[108],"other":[110],"domains.":[111],"Results:":[112],"Compared":[113],"original":[116],"work":[117],"C/C++":[119],"large":[121],"data,":[122],"CodeBERT\u2019s":[123],"performance":[124,160],"significantly":[131],"declines":[132],"languages,":[135],"signifying":[136],"negative":[138],"scarcity.":[142],"Regarding":[143],"remediation,":[144],"fail":[148],"improve":[150],"CodeBERT;":[151],"whereas,":[152],"showcases":[154],"promising":[155,187],"results,":[156],"substantially":[157],"enhancing":[158],"predictive":[159],"by":[161],"up":[162,170],"34.4%":[164],"function":[167],"level":[168],"53.5%":[172],"line":[175],"level.":[176],"Conclusion:":[177],"highlighted":[180],"challenge":[182],"made":[184],"first":[186],"step":[188],"prediction,":[192],"paving":[193],"way":[195],"future":[197],"research":[198],"this":[200],"direction.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
