{"id":"https://openalex.org/W4408047557","doi":"https://doi.org/10.1109/access.2025.3546700","title":"Finetuning Large Language Models for Vulnerability Detection","display_name":"Finetuning Large Language Models for Vulnerability Detection","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408047557","doi":"https://doi.org/10.1109/access.2025.3546700"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3546700","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3546700","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3546700","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116460299","display_name":"Aleksei Shestov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aleksei Shestov","raw_affiliation_strings":["Sber AI Lab, Moscow, Russia","Sber AI Lab, Vavilova St. 19, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sber AI Lab, Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"Sber AI Lab, Vavilova St. 19, Moscow, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025267049","display_name":"Rodion Levichev","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139213","display_name":"Research Institute of Semiconductor Devices","ror":"https://ror.org/03f2t9x29","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210139213"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Rodion Levichev","raw_affiliation_strings":["SaluteDevices, Moscow, Russia","Salute Devices, Vavilova St. 19, Moscow, Russia"],"raw_orcid":"https://orcid.org/0009-0003-6297-2470","affiliations":[{"raw_affiliation_string":"SaluteDevices, Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"Salute Devices, Vavilova St. 19, Moscow, Russia","institution_ids":["https://openalex.org/I4210139213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028453492","display_name":"Ravil Mussabayev","orcid":"https://orcid.org/0000-0003-1105-5990"},"institutions":[{"id":"https://openalex.org/I204275683","display_name":"Satbayev University","ror":"https://ror.org/020cpsb96","country_code":"KZ","type":"education","lineage":["https://openalex.org/I204275683"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Ravil Mussabayev","raw_affiliation_strings":["AI Research Lab, Satbayev University, Almaty, Kazakhstan","Sber AI Lab, Moscow, Russia","Satbayev University, Satbayev Str. 22, Almaty, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0003-1105-5990","affiliations":[{"raw_affiliation_string":"AI Research Lab, Satbayev University, Almaty, Kazakhstan","institution_ids":["https://openalex.org/I204275683"]},{"raw_affiliation_string":"Sber AI Lab, Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"Satbayev University, Satbayev Str. 22, Almaty, Kazakhstan","institution_ids":["https://openalex.org/I204275683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093836291","display_name":"Evgeny Maslov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089595","display_name":"Institute of Experimental Cardiology","ror":"https://ror.org/00bw4xw30","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1318325419","https://openalex.org/I4210089595"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Evgeny Maslov","raw_affiliation_strings":["Software Development Tools Cloud Technology Laboratory, Huawei Russian Research Institute, Moscow, Russia","Software Development Tools Cloud Technology Lab, Huawei Russian Research Institute, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software Development Tools Cloud Technology Laboratory, Huawei Russian Research Institute, Moscow, Russia","institution_ids":["https://openalex.org/I4210089595"]},{"raw_affiliation_string":"Software Development Tools Cloud Technology Lab, Huawei Russian Research Institute, Moscow, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Pavel Zadorozhny","orcid":"https://orcid.org/0009-0003-0381-2231"},"institutions":[{"id":"https://openalex.org/I4210139213","display_name":"Research Institute of Semiconductor Devices","ror":"https://ror.org/03f2t9x29","country_code":"RU","type":"facility","lineage":["https://openalex.org/I4210139213"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Pavel Zadorozhny","raw_affiliation_strings":["SaluteDevices, Moscow, Russia","Salute Devices, Vavilova St. 19, Moscow, Russia"],"raw_orcid":"https://orcid.org/0009-0003-0381-2231","affiliations":[{"raw_affiliation_string":"SaluteDevices, Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"Salute Devices, Vavilova St. 19, Moscow, Russia","institution_ids":["https://openalex.org/I4210139213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002156949","display_name":"Anton Cheshkov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089595","display_name":"Institute of Experimental Cardiology","ror":"https://ror.org/00bw4xw30","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1318325419","https://openalex.org/I4210089595"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Anton Cheshkov","raw_affiliation_strings":["Software Development Tools Cloud Technology Laboratory, Huawei Russian Research Institute, Moscow, Russia","Software Development Tools Cloud Technology Lab, Huawei Russian Research Institute, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Software Development Tools Cloud Technology Laboratory, Huawei Russian Research Institute, Moscow, Russia","institution_ids":["https://openalex.org/I4210089595"]},{"raw_affiliation_string":"Software Development Tools Cloud Technology Lab, Huawei Russian Research Institute, Moscow, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031261567","display_name":"Rustam Mussabayev","orcid":"https://orcid.org/0000-0001-7283-5144"},"institutions":[{"id":"https://openalex.org/I204275683","display_name":"Satbayev University","ror":"https://ror.org/020cpsb96","country_code":"KZ","type":"education","lineage":["https://openalex.org/I204275683"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Rustam Mussabayev","raw_affiliation_strings":["AI Research Lab, Satbayev University, Almaty, Kazakhstan","Sber AI Lab, Moscow, Russia","Satbayev University, Satbayev Str. 22, Almaty, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Research Lab, Satbayev University, Almaty, Kazakhstan","institution_ids":["https://openalex.org/I204275683"]},{"raw_affiliation_string":"Sber AI Lab, Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"Satbayev University, Satbayev Str. 22, Almaty, Kazakhstan","institution_ids":["https://openalex.org/I204275683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002964869","display_name":"Alymzhan Toleu","orcid":"https://orcid.org/0000-0001-9246-319X"},"institutions":[{"id":"https://openalex.org/I204275683","display_name":"Satbayev University","ror":"https://ror.org/020cpsb96","country_code":"KZ","type":"education","lineage":["https://openalex.org/I204275683"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Alymzhan Toleu","raw_affiliation_strings":["AI Research Lab, Satbayev University, Almaty, Kazakhstan","Satbayev University, Satbayev Str. 22, Almaty, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Research Lab, Satbayev University, Almaty, Kazakhstan","institution_ids":["https://openalex.org/I204275683"]},{"raw_affiliation_string":"Satbayev University, Satbayev Str. 22, Almaty, Kazakhstan","institution_ids":["https://openalex.org/I204275683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011719526","display_name":"Gulmira Tolegen","orcid":"https://orcid.org/0000-0001-8467-3699"},"institutions":[{"id":"https://openalex.org/I204275683","display_name":"Satbayev University","ror":"https://ror.org/020cpsb96","country_code":"KZ","type":"education","lineage":["https://openalex.org/I204275683"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Gulmira Tolegen","raw_affiliation_strings":["AI Research Lab, Satbayev University, Almaty, Kazakhstan","Satbayev University, Satbayev Str. 22, Almaty, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0001-8467-3699","affiliations":[{"raw_affiliation_string":"AI Research Lab, Satbayev University, Almaty, Kazakhstan","institution_ids":["https://openalex.org/I204275683"]},{"raw_affiliation_string":"Satbayev University, Satbayev Str. 22, Almaty, Kazakhstan","institution_ids":["https://openalex.org/I204275683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053595206","display_name":"Alexander Krassovitskiy","orcid":"https://orcid.org/0000-0003-2948-374X"},"institutions":[{"id":"https://openalex.org/I204275683","display_name":"Satbayev University","ror":"https://ror.org/020cpsb96","country_code":"KZ","type":"education","lineage":["https://openalex.org/I204275683"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Alexander Krassovitskiy","raw_affiliation_strings":["AI Research Lab, Satbayev University, Almaty, Kazakhstan","Satbayev University, Satbayev Str. 22, Almaty, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Research Lab, Satbayev University, Almaty, Kazakhstan","institution_ids":["https://openalex.org/I204275683"]},{"raw_affiliation_string":"Satbayev University, Satbayev Str. 22, Almaty, Kazakhstan","institution_ids":["https://openalex.org/I204275683"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":139.1767,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.99987969,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"13","issue":null,"first_page":"38889","last_page":"38900"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12479","display_name":"Web Application Security Vulnerabilities","score":0.8402000069618225,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.8402000069618225,"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":0.765999972820282,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.7502999901771545,"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":0.7573405504226685},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.5080366134643555},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.2437327802181244}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573405504226685},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.5080366134643555},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2437327802181244}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3546700","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3546700","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:178876c696a44d0d97e9333a520ca2f6","is_oa":true,"landing_page_url":"https://doaj.org/article/178876c696a44d0d97e9333a520ca2f6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 38889-38900 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3546700","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3546700","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2556231585","display_name":null,"funder_award_id":"BR21882268","funder_id":"https://openalex.org/F4320322726","funder_display_name":"Ministry of Education and Science of the Republic of Kazakhstan"}],"funders":[{"id":"https://openalex.org/F4320322726","display_name":"Ministry of Education and Science of the Republic of Kazakhstan","ror":"https://ror.org/03pj6ge82"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2963351448","https://openalex.org/W2963926786","https://openalex.org/W3166095789","https://openalex.org/W3183469243","https://openalex.org/W4286331380","https://openalex.org/W4312436517","https://openalex.org/W4380763529","https://openalex.org/W4384302803","https://openalex.org/W4384345694","https://openalex.org/W4385562549","https://openalex.org/W4388212383","https://openalex.org/W4390679741","https://openalex.org/W4393406994","https://openalex.org/W4405543707","https://openalex.org/W6773936880","https://openalex.org/W6796581206","https://openalex.org/W6852183785","https://openalex.org/W6852746770","https://openalex.org/W6852832533","https://openalex.org/W6854013397"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","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"],"abstract_inverted_index":{"This":[0,144],"paper":[1],"presents":[2],"the":[3,12,28,56,97,114,124,128,146],"results":[4],"of":[5,14,27,99],"finetuning":[6,113,152],"large":[7,153],"language":[8,155],"models":[9,156],"(LLMs)":[10],"for":[11,35,103,148,157],"task":[13],"detecting":[15],"vulnerabilities":[16],"in":[17,81,106],"Java":[18],"source":[19,107,159],"code.":[20,108],"We":[21],"leverage":[22],"WizardCoder,":[23,118],"a":[24],"recent":[25],"improvement":[26,80],"state-of-the-art":[29,115],"LLM":[30],"StarCoder,":[31],"and":[32,84,89,131,136],"adapt":[33],"it":[34],"vulnerability":[36,91,104,141],"detection":[37,105,142],"through":[38],"further":[39],"finetuning.":[40],"To":[41],"accelerate":[42],"training,":[43],"we":[44,50,66],"modify":[45],"WizardCoder\u2019s":[46],"training":[47,53,121,129],"procedure,":[48],"also":[49,67],"investigate":[51],"optimal":[52],"regimes.":[54],"For":[55],"imbalanced":[57,90],"dataset":[58],"with":[59],"many":[60],"more":[61],"negative":[62],"examples":[63],"than":[64],"positive,":[65],"explore":[68],"different":[69],"techniques":[70],"to":[71],"improve":[72],"classification":[73],"performance.":[74],"The":[75,109],"finetuned":[76],"WizardCoder":[77],"model":[78],"achieves":[79],"ROC":[82],"AUC":[83],"F1":[85],"measures":[86],"on":[87,139],"balanced":[88],"datasets":[92],"over":[93],"CodeBERT-like":[94],"model,":[95],"demonstrating":[96],"effectiveness":[98],"adapting":[100],"pretrained":[101,154],"LLMs":[102],"key":[110],"contributions":[111],"are":[112],"code":[116,160],"LLM,":[117],"increasing":[119],"its":[120],"speed":[122],"without":[123],"performance":[125,138],"harm,":[126],"optimizing":[127],"procedure":[130],"regimes,":[132],"handling":[133],"class":[134],"imbalance,":[135],"improving":[137],"difficult":[140],"datasets.":[143],"demonstrates":[145],"potential":[147],"transfer":[149],"learning":[150],"by":[151],"specialized":[158],"analysis":[161],"tasks.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":48},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
