{"id":"https://openalex.org/W4414363420","doi":"https://doi.org/10.1145/3768582","title":"PVDetector: Pretrained Vulnerability Detection on Vulnerability-enriched Code Semantic Graph","display_name":"PVDetector: Pretrained Vulnerability Detection on Vulnerability-enriched Code Semantic Graph","publication_year":2025,"publication_date":"2025-09-19","ids":{"openalex":"https://openalex.org/W4414363420","doi":"https://doi.org/10.1145/3768582"},"language":"en","primary_location":{"id":"doi:10.1145/3768582","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3768582","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3768582","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021084454","display_name":"Jiachong Li","orcid":"https://orcid.org/0000-0002-0784-3882"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayuan Li","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0002-0784-3882","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China and School of Cyber Security, University of Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101581995","display_name":"Lei Cui","orcid":"https://orcid.org/0000-0002-8478-3297"},"institutions":[{"id":"https://openalex.org/I134052481","display_name":"Harbin Normal University","ror":"https://ror.org/0270y6950","country_code":"CN","type":"education","lineage":["https://openalex.org/I134052481"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Cui","raw_affiliation_strings":["Guangxi Normal University, Guilin, China and Harbin Institute of Technology, Harbin, China","Guangxi Normal University, China and Harbin Institute of Technology, China"],"raw_orcid":"https://orcid.org/0000-0002-8478-3297","affiliations":[{"raw_affiliation_string":"Guangxi Normal University, Guilin, China and Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I134052481"]},{"raw_affiliation_string":"Guangxi Normal University, China and Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I134052481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109755000","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0002-1135-2031"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","Institute of Information Engineering, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0002-1135-2031","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100371842","display_name":"Lun Li","orcid":"https://orcid.org/0000-0002-6700-7835"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lun Li","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","Institute of Information Engineering, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0002-6700-7835","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074449850","display_name":"Rongrong Xi","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongrong Xi","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","Institute of Information Engineering, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0009-0002-1708-1487","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087012171","display_name":"Hongsong Zhu","orcid":"https://orcid.org/0000-0003-3720-7403"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongsong Zhu","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","Institute of Information Engineering, Chinese Academy of Sciences, China"],"raw_orcid":"https://orcid.org/0000-0003-3720-7403","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0267,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89756542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"35","issue":"6","first_page":"1","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9991999864578247,"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/T10734","display_name":"Information and Cyber Security","score":0.9966999888420105,"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/semantics","display_name":"Semantics (computer science)","score":0.5662999749183655},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5620999932289124},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.5569000244140625},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5083000063896179},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.46700000762939453},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.46650001406669617},{"id":"https://openalex.org/keywords/static-program-analysis","display_name":"Static program analysis","score":0.3077000081539154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8917999863624573},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5662999749183655},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5620999932289124},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.5569000244140625},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5083000063896179},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46700000762939453},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46650001406669617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4372999966144562},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.359499990940094},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3262999951839447},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.3077000081539154},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C2777561058","wikidata":"https://www.wikidata.org/wiki/Q2652119","display_name":"Program comprehension","level":4,"score":0.2669000029563904},{"id":"https://openalex.org/C16311509","wikidata":"https://www.wikidata.org/wiki/Q4148050","display_name":"Dependency graph","level":3,"score":0.2574000060558319},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.25450000166893005},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3768582","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3768582","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3768582","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3768582","pdf_url":null,"source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F183612021","display_name":"Institute of Information Engineering, Chinese Academy of Sciences","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W40327287","https://openalex.org/W1543330234","https://openalex.org/W2027887391","https://openalex.org/W2043837581","https://openalex.org/W2753750754","https://openalex.org/W2777430404","https://openalex.org/W2804700615","https://openalex.org/W2885030880","https://openalex.org/W2899575547","https://openalex.org/W2923698584","https://openalex.org/W2997258927","https://openalex.org/W2998879504","https://openalex.org/W3117923638","https://openalex.org/W3166095789","https://openalex.org/W3176789817","https://openalex.org/W3191605668","https://openalex.org/W4238623774","https://openalex.org/W4238901036","https://openalex.org/W4288269198","https://openalex.org/W4292258179","https://openalex.org/W4299527668","https://openalex.org/W4302070056","https://openalex.org/W4319083508","https://openalex.org/W4379381391","https://openalex.org/W4393029443","https://openalex.org/W4397049698","https://openalex.org/W4402310141","https://openalex.org/W4402443087","https://openalex.org/W4411337147"],"related_works":[],"abstract_inverted_index":{"Automated":[0],"vulnerability":[1,64,73,109],"detection":[2],"is":[3],"a":[4,55,80],"critical":[5],"issue":[6],"in":[7,26,44,143,155,158,162],"software":[8,27,184],"security.":[9],"The":[10],"advent":[11],"of":[12,97,123],"Deep":[13],"Learning":[14],"(DL)":[15],"has":[16],"led":[17],"to":[18,23,41,119,140,182],"numerous":[19],"studies":[20],"employing":[21],"DL":[22],"detect":[24,141],"vulnerabilities":[25,142],"source":[28],"code.":[29],"However,":[30],"existing":[31],"approaches":[32],"still":[33],"perform":[34],"poorly,":[35],"particularly":[36],"with":[37],"real-world":[38],"vulnerabilities,":[39,189],"due":[40],"the":[42,95,121,130],"difficulty":[43],"accurately":[45,90],"capturing":[46,103],"their":[47],"properties.":[48],"To":[49],"this":[50],"end,":[51],"we":[52,112],"introduce":[53,113],"PVDetector,":[54],"DL-based":[56],"approach":[57],"that":[58,149,195],"utilizes":[59],"rich":[60],"code":[61,69],"semantics,":[62],"incorporates":[63],"knowledge,":[65],"and":[66,100,108,127,160,170],"leverages":[67],"pretrained":[68],"representations":[70],"for":[71],"precise":[72],"detection.":[74],"At":[75],"its":[76],"core,":[77],"PVDetector":[78,150,186],"employs":[79],"new":[81],"model":[82],"called":[83],"Vulnerability-enriched":[84],"Code":[85],"Semantic":[86],"Graph":[87],"(VCSG),":[88],"which":[89],"characterizes":[91],"functions":[92],"by":[93,153],"distinguishing":[94],"semantics":[96,122],"identical":[98],"variables":[99,128],"more":[101],"finely":[102],"control":[104],"dependencies,":[105,107],"data":[106],"relationships.":[110],"Additionally,":[111,164],"four":[114],"pretraining":[115,134],"tasks":[116,135],"specifically":[117],"designed":[118],"learn":[120],"control,":[124],"data,":[125],"vulnerability,":[126],"from":[129],"VCSG":[131],"model.":[132],"These":[133],"significantly":[136],"enhance":[137],"PVDetector\u2019s":[138],"capability":[139],"downstream":[144],"tasks.":[145],"Experimental":[146],"results":[147],"indicate":[148],"outperforms":[151],"SOTAs":[152],"5.0\u201312.5%":[154],"precision,":[156],"0.2\u20139.7%":[157],"recall,":[159],"3.0\u201315.1%":[161],"F1-score.":[163],"it":[165],"supports":[166],"six":[167],"programming":[168],"languages":[169],"demonstrates":[171],"high":[172],"efficiency":[173],"(e.g.,":[174],"10.6":[175],"\\(\\times\\)":[176],"faster":[177],"than":[178],"DeepDFA).":[179],"When":[180],"applied":[181],"seven":[183],"products,":[185],"discovered":[187],"55":[188],"including":[190],"10":[191],"silently":[192],"patched":[193],"flaws":[194],"had":[196],"not":[197],"been":[198],"previously":[199],"reported.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
