{"id":"https://openalex.org/W4394746043","doi":"https://doi.org/10.1145/3597503.3639116","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":2024,"publication_date":"2024-04-12","ids":{"openalex":"https://openalex.org/W4394746043","doi":"https://doi.org/10.1145/3597503.3639116"},"language":"en","primary_location":{"id":"doi:10.1145/3597503.3639116","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3597503.3639116","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3597503.3639116","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 IEEE/ACM 46th International Conference on Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3597503.3639116","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030441764","display_name":"Yu Nong","orcid":"https://orcid.org/0000-0002-8598-5181"},"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":true,"raw_author_name":"Yu Nong","raw_affiliation_strings":["Washington State University, Pullman, Washington, USA"],"affiliations":[{"raw_affiliation_string":"Washington State University, Pullman, Washington, USA","institution_ids":["https://openalex.org/I72951846"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102027189","display_name":"Richard Fang","orcid":"https://orcid.org/0009-0009-8104-9917"},"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":"Richard Fang","raw_affiliation_strings":["Washington State University, Pullman, Washington, USA"],"affiliations":[{"raw_affiliation_string":"Washington State University, Pullman, Washington, USA","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"},"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":"Guangbei Yi","raw_affiliation_strings":["Washington State University, Pullman, Washington, USA"],"affiliations":[{"raw_affiliation_string":"Washington State University, Pullman, Washington, USA","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"},"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":"Kunsong Zhao","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, China","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"},"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":"Xiapu Luo","raw_affiliation_strings":["The Hong Kong Polytechnic University, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352703","display_name":"Feng Chen","orcid":"https://orcid.org/0000-0002-4508-5963"},"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":"Feng Chen","raw_affiliation_strings":["The University of Texas at Dallas, Dallas, Texas, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas, Dallas, Texas, USA","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"},"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":"Haipeng Cai","raw_affiliation_strings":["Washington State University, Pullman, Washington, USA"],"affiliations":[{"raw_affiliation_string":"Washington State University, Pullman, Washington, USA","institution_ids":["https://openalex.org/I72951846"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5030441764"],"corresponding_institution_ids":["https://openalex.org/I72951846"],"apc_list":null,"apc_paid":null,"fwci":16.7956,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.99073718,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9979000091552734,"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":0.9919000267982483,"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":0.7018467783927917},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5419501066207886},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.5042093992233276},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.49939990043640137},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4839246869087219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48123741149902344},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47728362679481506},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.47223424911499023},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.46999797224998474},{"id":"https://openalex.org/keywords/vulnerability-assessment","display_name":"Vulnerability assessment","score":0.42049849033355713},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.41486644744873047},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3824898600578308},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.14070996642112732},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12553194165229797},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.0810854434967041}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7018467783927917},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5419501066207886},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.5042093992233276},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.49939990043640137},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4839246869087219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48123741149902344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47728362679481506},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.47223424911499023},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46999797224998474},{"id":"https://openalex.org/C167063184","wikidata":"https://www.wikidata.org/wiki/Q1400839","display_name":"Vulnerability assessment","level":3,"score":0.42049849033355713},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.41486644744873047},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3824898600578308},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.14070996642112732},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12553194165229797},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0810854434967041},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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},{"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/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"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/C137176749","wikidata":"https://www.wikidata.org/wiki/Q4105337","display_name":"Psychological resilience","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3597503.3639116","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3597503.3639116","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3597503.3639116","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 IEEE/ACM 46th International Conference on Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3597503.3639116","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3597503.3639116","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3597503.3639116","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 IEEE/ACM 46th International Conference on Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"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"},{"id":"https://openalex.org/G8998121839","display_name":null,"funder_award_id":"911NF","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4394746043.pdf","grobid_xml":"https://content.openalex.org/works/W4394746043.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W2079887492","https://openalex.org/W2493916176","https://openalex.org/W2624697062","https://openalex.org/W2781491433","https://openalex.org/W2885030880","https://openalex.org/W2897042325","https://openalex.org/W2898930465","https://openalex.org/W2911495555","https://openalex.org/W2913954081","https://openalex.org/W2969186282","https://openalex.org/W2979679630","https://openalex.org/W2998879504","https://openalex.org/W3014251208","https://openalex.org/W3082924206","https://openalex.org/W3091588759","https://openalex.org/W3098605233","https://openalex.org/W3101228802","https://openalex.org/W3156480510","https://openalex.org/W3162927918","https://openalex.org/W3163206498","https://openalex.org/W3166095789","https://openalex.org/W3177116043","https://openalex.org/W3183469243","https://openalex.org/W3183985440","https://openalex.org/W3188635326","https://openalex.org/W3191226037","https://openalex.org/W3194346579","https://openalex.org/W3198685994","https://openalex.org/W3212771748","https://openalex.org/W4281386687","https://openalex.org/W4284667406","https://openalex.org/W4284697810","https://openalex.org/W4292982707","https://openalex.org/W4296079499","https://openalex.org/W4308641648","https://openalex.org/W4308642993","https://openalex.org/W4308643013","https://openalex.org/W4308643022","https://openalex.org/W4312436517","https://openalex.org/W4312969325","https://openalex.org/W4313563712","https://openalex.org/W4384345694","https://openalex.org/W4388867344","https://openalex.org/W4389612565","https://openalex.org/W6738959025"],"related_works":["https://openalex.org/W1883246888","https://openalex.org/W2370114625","https://openalex.org/W1756374135","https://openalex.org/W2947584067","https://openalex.org/W3118510577","https://openalex.org/W2280562859","https://openalex.org/W230721595","https://openalex.org/W3157230915","https://openalex.org/W1496728123","https://openalex.org/W2062873522"],"abstract_inverted_index":{"Accompanying":[0],"the":[1,10,46,50,74,113],"successes":[2],"of":[3,12,17,26,41,64,118],"learning-based":[4],"defensive":[5],"software":[6],"vulnerability":[7,66],"analyses":[8],"is":[9],"lack":[11],"large":[13],"and":[14,94,104,126],"quality":[15],"sets":[16],"labeled":[18],"vulnerable":[19],"program":[20],"samples,":[21],"which":[22,78],"impedes":[23],"further":[24],"advancement":[25],"those":[27],"defenses.":[28],"Existing":[29],"automated":[30],"sample":[31],"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],"high":[47],"noise":[48],"in":[49,77,112],"generated":[51],"samples.":[52],"This":[53],"paper":[54],"proposes":[55],"VGX,":[56],"a":[57,69,84,89],"new":[58,90,97],"technique":[59],"aimed":[60],"for":[61,100],"large-scale":[62],"high-quality":[65],"datasets.":[67],"Given":[68],"normal":[70],"program,":[71],"VGX":[72,107],"identifies":[73],"code":[75,102,110],"contexts":[76,115],"vulnerabilities":[79],"can":[80],"be":[81],"injected,":[82],"using":[83,116],"customized":[85],"Transformer":[86],"featured":[87],"with":[88],"value-flow-based":[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],"both":[123],"historical":[124],"fixes":[125],"human":[127],"knowledge":[128],"about":[129],"real-world":[130],"vulnerabilities.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":7}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}