{"id":"https://openalex.org/W4387947162","doi":"https://doi.org/10.48550/arxiv.2310.15436","title":"VGX: Large-Scale Sample Generation for Boosting Learning-Based Software Vulnerability Analyses","display_name":"VGX: Large-Scale Sample Generation for Boosting Learning-Based Software Vulnerability Analyses","publication_year":2023,"publication_date":"2023-10-24","ids":{"openalex":"https://openalex.org/W4387947162","doi":"https://doi.org/10.48550/arxiv.2310.15436"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.15436","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.15436","pdf_url":"https://arxiv.org/pdf/2310.15436","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.15436","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Nong, Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nong, Yu","raw_affiliation_strings":["Washington State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington State University","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104281614","display_name":"Richard Fang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fang, Richard","raw_affiliation_strings":["Washington State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington State University","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102800591","display_name":"Guangbei Yi","orcid":"https://orcid.org/0009-0009-6679-5153","observed_orcids":["https://orcid.org/0009-0009-6679-5153"]},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi, Guangbei","raw_affiliation_strings":["Washington State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington State University","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022643319","display_name":"Kunsong Zhao","orcid":"https://orcid.org/0000-0001-9886-0460","observed_orcids":["https://orcid.org/0000-0001-9886-0460"]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhao, Kunsong","raw_affiliation_strings":["Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400376","display_name":"Xiapu Luo","orcid":"https://orcid.org/0000-0002-9082-3208","observed_orcids":["https://orcid.org/0000-0002-9082-3208"]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Luo, Xiapu","raw_affiliation_strings":["Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113146240","display_name":"Feng Chen","orcid":"https://orcid.org/0000-0003-2915-599X","observed_orcids":["https://orcid.org/0000-0003-2915-599X"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Feng","raw_affiliation_strings":["The University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076081056","display_name":"Haipeng Cai","orcid":"https://orcid.org/0000-0002-5224-9970","observed_orcids":["https://orcid.org/0000-0002-5224-9970"]},"institutions":[{"id":"https://openalex.org/I72951846","display_name":"Washington State University","ror":"https://ror.org/05dk0ce17","country_code":"US","type":"education","lineage":["https://openalex.org/I72951846"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cai, Haipeng","raw_affiliation_strings":["Washington State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington State University","institution_ids":["https://openalex.org/I72951846"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.43070000410079956,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.43070000410079956,"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":0.4027999937534332,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.07599999755620956,"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/injection-vulnerabilities","display_name":"injection vulnerabilities","score":0.48500001430511475},{"id":"https://openalex.org/keywords/vulnerability-detection","display_name":"vulnerability detection","score":0.7390000224113464},{"id":"https://openalex.org/keywords/vulnerability-localization","display_name":"vulnerability localization","score":0.953000009059906},{"id":"https://openalex.org/keywords/vulnerability-remediation","display_name":"vulnerability remediation","score":0.9739999771118164},{"id":"https://openalex.org/keywords/linux-kernel","display_name":"Linux kernel","score":0.5759999752044678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6060704588890076},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5202694535255432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5161570310592651},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5015163421630859},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4392394423484802},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.4362871050834656},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4353964924812317},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41250866651535034},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35928380489349365},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17061930894851685},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.12169542908668518},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09453043341636658},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.15436","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.15436","pdf_url":"https://arxiv.org/pdf/2310.15436","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.15436","doi":"https://doi.org/10.48550/arxiv.2310.15436","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.15436","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.15436","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.15436","pdf_url":"https://arxiv.org/pdf/2310.15436","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1432373144","display_name":null,"funder_award_id":"W911NF-21-1-","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G2644709866","display_name":null,"funder_award_id":"W911NF-21-1-0027","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387947162.pdf","grobid_xml":"https://content.openalex.org/works/W4387947162.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"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":{"Accompanying":[0],"the":[1,10,46,50,74,113,238],"successes":[2],"of":[3,12,17,26,41,64,118],"learning-based":[4],"defensive":[5],"software":[6],"vulnerability":[7,66,175,219],"analyses":[8],"is":[9],"lack":[11],"large":[13],"and":[14,94,104,126,141,148,178,198],"quality":[15],"sets":[16],"labeled":[18],"vulnerable":[19,160],"program":[20],"samples,":[21,161],"which":[22,78,163],"impedes":[23],"further":[24],"advancement":[25],"those":[27,206],"defenses.":[28],"Existing":[29],"automated":[30],"sample":[31,155],"generation":[32,63],"approaches":[33],"have":[34],"shown":[35],"potentials":[36],"yet":[37],"still":[38],"fall":[39],"short":[40],"practical":[42],"expectations":[43],"due":[44],"to":[45,133,168,208],"high":[47],"noise":[48],"in":[49,77,112,227],"generated":[51,158],"samples.":[52],"This":[53],"paper":[54],"proposes":[55],"VGX,":[56],"a":[57,69,84,89,217],"new":[58,90,97],"technique":[59],"aimed":[60],"for":[61,100,185],"large-scale":[62],"high-quality":[65],"datasets.":[67],"Given":[68],"normal":[70],"program,":[71],"VGX":[72,107,143,157],"identifies":[73],"code":[75,102,110],"contexts":[76,115],"vulnerabilities":[79,225],"can":[80],"be":[81,235],"injected,":[82],"using":[83,116],"customized":[85],"Transformer":[86],"featured":[87],"with":[88],"value-flowbased":[91],"position":[92],"encoding":[93],"pre-trained":[95],"against":[96],"objectives":[98],"particularly":[99],"learning":[101],"structure":[103],"context.":[105],"Then,":[106],"materializes":[108],"vulnerability-injection":[109],"editing":[111],"identified":[114],"patterns":[117],"such":[119],"edits":[120],"obtained":[121],"from":[122,162],"both":[123],"historical":[124],"fixes":[125],"human":[127],"knowledge":[128],"about":[129],"real-world":[130,224],"vulnerabilities.":[131],"Compared":[132],"four":[134],"state-of-the-art":[135],"(SOTA)":[136],"baselines":[137],"(pattern-,":[138],"Transformer-,":[139],"GNN-,":[140],"pattern+Transformer-based),":[142],"achieved":[144,190],"99.09-890.06%":[145],"higher":[146,150,192,195,200],"F1":[147],"22.45%-328.47%":[149],"label":[151],"accuracy.":[152],"For":[153],"in-the-wild":[154],"production,":[156],"150,392":[159],"we":[164],"randomly":[165],"chose":[166],"10%":[167],"assess":[169],"how":[170],"much":[171],"these":[172,186],"samples":[173,207,214],"help":[174],"detection,":[176],"localization,":[177],"repair.":[179],"Our":[180],"results":[181],"show":[182],"SOTA":[183,218],"techniques":[184],"three":[187],"application":[188],"tasks":[189],"19.15-330.80%":[191],"F1,":[193],"12.86-19.31%":[194],"top-10":[196],"accuracy,":[197,202],"85.02-99.30%":[199],"top-50":[201],"respectively,":[203],"by":[204,237],"adding":[205],"their":[209],"original":[210,239],"training":[211],"data.":[212],"These":[213],"also":[215],"helped":[216],"detector":[220],"discover":[221],"13":[222],"more":[223],"(CVEs)":[226],"critical":[228],"systems":[229],"(e.g.,":[230],"Linux":[231],"kernel)":[232],"that":[233],"would":[234],"missed":[236],"model.":[240]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2023-10-26T00:00:00"}