{"id":"https://openalex.org/W4406461825","doi":"https://doi.org/10.1109/bigdata62323.2024.10825609","title":"EnStack: An Ensemble Stacking Framework of Large Language Models for Enhanced Vulnerability Detection in Source Code","display_name":"EnStack: An Ensemble Stacking Framework of Large Language Models for Enhanced Vulnerability Detection in Source Code","publication_year":2024,"publication_date":"2024-12-15","ids":{"openalex":"https://openalex.org/W4406461825","doi":"https://doi.org/10.1109/bigdata62323.2024.10825609"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata62323.2024.10825609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"article","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/A5114987965","display_name":"Shahriyar Zaman Ridoy","orcid":null},"institutions":[{"id":"https://openalex.org/I157386601","display_name":"North South University","ror":"https://ror.org/05wdbfp45","country_code":"BD","type":"education","lineage":["https://openalex.org/I157386601"]}],"countries":["BD"],"is_corresponding":true,"raw_author_name":"Shahriyar Zaman Ridoy","raw_affiliation_strings":["North South University,Department of Electrical and Computer Engineering,Dhaka,Bangladesh"],"affiliations":[{"raw_affiliation_string":"North South University,Department of Electrical and Computer Engineering,Dhaka,Bangladesh","institution_ids":["https://openalex.org/I157386601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093214705","display_name":"Md. Shazzad Hossain Shaon","orcid":"https://orcid.org/0009-0008-2491-1622"},"institutions":[{"id":"https://openalex.org/I177721651","display_name":"Oakland University","ror":"https://ror.org/01ythxj32","country_code":"US","type":"education","lineage":["https://openalex.org/I177721651"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md. Shazzad Hossain Shaon","raw_affiliation_strings":["Oakland University,Department of Computer Science and Engineering,Rochester,MI,USA,48309"],"affiliations":[{"raw_affiliation_string":"Oakland University,Department of Computer Science and Engineering,Rochester,MI,USA,48309","institution_ids":["https://openalex.org/I177721651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053225136","display_name":"Alfredo Cuzzocrea","orcid":"https://orcid.org/0000-0002-7104-6415"},"institutions":[{"id":"https://openalex.org/I45204951","display_name":"University of Calabria","ror":"https://ror.org/02rc97e94","country_code":"IT","type":"education","lineage":["https://openalex.org/I45204951"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alfredo Cuzzocrea","raw_affiliation_strings":["University of Calabria,Rende,Italy,iDEA Lab"],"affiliations":[{"raw_affiliation_string":"University of Calabria,Rende,Italy,iDEA Lab","institution_ids":["https://openalex.org/I45204951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015055011","display_name":"Mst Shapna Akter","orcid":"https://orcid.org/0000-0002-9859-6265"},"institutions":[{"id":"https://openalex.org/I177721651","display_name":"Oakland University","ror":"https://ror.org/01ythxj32","country_code":"US","type":"education","lineage":["https://openalex.org/I177721651"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mst Shapna Akter","raw_affiliation_strings":["Oakland University,Department of Computer Science,MI,USA"],"affiliations":[{"raw_affiliation_string":"Oakland University,Department of Computer Science,MI,USA","institution_ids":["https://openalex.org/I177721651"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114987965"],"corresponding_institution_ids":["https://openalex.org/I157386601"],"apc_list":null,"apc_paid":null,"fwci":6.3826,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.96734285,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6356","last_page":"6364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9965999722480774,"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":0.9965999722480774,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9961000084877014,"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"}},{"id":"https://openalex.org/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9933000206947327,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.693483293056488},{"id":"https://openalex.org/keywords/stacking","display_name":"Stacking","score":0.685412585735321},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5885912775993347},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5718441009521484},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.5630187392234802},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.35230210423469543},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.2546807527542114},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1051187515258789}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.693483293056488},{"id":"https://openalex.org/C33347731","wikidata":"https://www.wikidata.org/wiki/Q285210","display_name":"Stacking","level":2,"score":0.685412585735321},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5885912775993347},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5718441009521484},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.5630187392234802},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.35230210423469543},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2546807527542114},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1051187515258789},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata62323.2024.10825609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata62323.2024.10825609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1992114977","https://openalex.org/W2295598076","https://openalex.org/W2562607067","https://openalex.org/W2748690817","https://openalex.org/W2781491433","https://openalex.org/W2800702583","https://openalex.org/W2810411302","https://openalex.org/W2885030880","https://openalex.org/W2896262751","https://openalex.org/W2921519987","https://openalex.org/W2962960733","https://openalex.org/W2963935794","https://openalex.org/W2972135640","https://openalex.org/W2984432074","https://openalex.org/W2998879504","https://openalex.org/W3033777149","https://openalex.org/W3084813481","https://openalex.org/W3090702224","https://openalex.org/W3098605233","https://openalex.org/W3099644249","https://openalex.org/W3101228802","https://openalex.org/W3119507053","https://openalex.org/W3136874603","https://openalex.org/W4205416355","https://openalex.org/W4205648436","https://openalex.org/W4205796731","https://openalex.org/W4213251304","https://openalex.org/W4221166942","https://openalex.org/W4312248293","https://openalex.org/W4312326656","https://openalex.org/W4312690534","https://openalex.org/W4391769278","https://openalex.org/W4393406994","https://openalex.org/W6767260250","https://openalex.org/W6783227185"],"related_works":["https://openalex.org/W2035329725","https://openalex.org/W2070875936","https://openalex.org/W4250391473","https://openalex.org/W4302292679","https://openalex.org/W4241625287","https://openalex.org/W2050788868","https://openalex.org/W4295885776","https://openalex.org/W2027634686","https://openalex.org/W3036164038","https://openalex.org/W3081644756"],"abstract_inverted_index":{"Automated":[0],"detection":[1,46],"of":[2,20,57,63,69,114,145],"software":[3],"vulnerabilities":[4,150],"is":[5],"critical":[6],"for":[7,170],"enhancing":[8,117],"security,":[9],"yet":[10],"existing":[11,128],"methods":[12],"often":[13],"struggle":[14],"with":[15,130],"the":[16,54,59,66,76,112,143],"complexity":[17],"and":[18,42,65,80,96,138,148,167],"diversity":[19],"modern":[21],"codebases.":[22],"In":[23],"this":[24],"paper,":[25],"we":[26,98],"propose":[27],"a":[28,164],"novel":[29],"ensemble":[30,122,160],"stacking":[31,161],"approach":[32,162],"that":[33,104,158],"synergizes":[34],"multiple":[35],"pre-trained":[36],"large":[37],"language":[38],"models":[39,74,106],"(LLMs)\u2014CodeBERT,":[40],"GraphCodeBERT,":[41,64],"UniXcoder\u2014to":[43],"improve":[44],"vulnerability":[45,172],"in":[47,133,151],"source":[48],"code.":[49],"Our":[50,121],"method":[51],"uniquely":[52],"combines":[53],"semantic":[55],"understanding":[56],"CodeBERT,":[58],"structural":[60],"code":[61,102],"representations":[62],"cross-modal":[67],"capabilities":[68],"UniXcoder.":[70],"By":[71],"fine-tuning":[72],"these":[73],"on":[75],"Draper":[77],"VDISC":[78],"dataset":[79],"integrating":[81],"their":[82],"predictions":[83],"using":[84],"meta-classifiers":[85,110],"such":[86],"as":[87],"Logistic":[88],"Regression,":[89],"Support":[90],"Vector":[91],"Machines":[92],"(SVM),":[93],"Random":[94],"Forest,":[95],"XGBoost,":[97],"effectively":[99],"capture":[100],"complex":[101,149],"patterns":[103],"individual":[105],"may":[107],"miss.":[108],"The":[109,155],"aggregate":[111],"strengths":[113],"each":[115],"model,":[116],"overall":[118],"predictive":[119],"performance.":[120],"demonstrates":[123],"significant":[124],"performance":[125],"gains":[126],"over":[127],"methods,":[129],"notable":[131],"improvements":[132],"accuracy,":[134],"precision,":[135],"recall,":[136],"F1-score,":[137],"AUC-score.":[139],"This":[140],"advancement":[141],"addresses":[142],"challenge":[144],"detecting":[146],"subtle":[147],"diverse":[152],"programming":[153],"contexts.":[154],"results":[156],"suggest":[157],"our":[159],"offers":[163],"more":[165],"robust":[166],"comprehensive":[168],"solution":[169],"automated":[171],"detection,":[173],"potentially":[174],"influencing":[175],"future":[176],"AI-driven":[177],"security":[178],"practices.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}