{"id":"https://openalex.org/W4412375763","doi":"https://doi.org/10.1109/access.2025.3587104","title":"On the Effectiveness of Automatic Code Generation for Synthetic Dataset Creation","display_name":"On the Effectiveness of Automatic Code Generation for Synthetic Dataset Creation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412375763","doi":"https://doi.org/10.1109/access.2025.3587104"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3587104","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3587104","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.2025.3587104","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017608443","display_name":"Josh Mitchell","orcid":null},"institutions":[{"id":"https://openalex.org/I125467818","display_name":"Dakota State University","ror":"https://ror.org/016yv6y68","country_code":"US","type":"education","lineage":["https://openalex.org/I125467818"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Josh Mitchell","raw_affiliation_strings":["Department of Computer and Cyber Sciences, Dakota State University, Madison, SD, USA"],"raw_orcid":"https://orcid.org/0009-0009-1397-0771","affiliations":[{"raw_affiliation_string":"Department of Computer and Cyber Sciences, Dakota State University, Madison, SD, USA","institution_ids":["https://openalex.org/I125467818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107611156","display_name":"Varghese Vaidyan","orcid":"https://orcid.org/0000-0002-9737-242X"},"institutions":[{"id":"https://openalex.org/I125467818","display_name":"Dakota State University","ror":"https://ror.org/016yv6y68","country_code":"US","type":"education","lineage":["https://openalex.org/I125467818"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Varghese Mathew Vaidyan","raw_affiliation_strings":["Department of Computer and Cyber Sciences, Dakota State University, Madison, SD, USA"],"raw_orcid":"https://orcid.org/0000-0002-9737-242X","affiliations":[{"raw_affiliation_string":"Department of Computer and Cyber Sciences, Dakota State University, Madison, SD, USA","institution_ids":["https://openalex.org/I125467818"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101496890","display_name":"Yong Wang","orcid":"https://orcid.org/0000-0002-1962-4847"},"institutions":[{"id":"https://openalex.org/I125467818","display_name":"Dakota State University","ror":"https://ror.org/016yv6y68","country_code":"US","type":"education","lineage":["https://openalex.org/I125467818"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yong Wang","raw_affiliation_strings":["Department of Computer and Cyber Sciences, Dakota State University, Madison, SD, USA"],"raw_orcid":"https://orcid.org/0000-0002-1962-4847","affiliations":[{"raw_affiliation_string":"Department of Computer and Cyber Sciences, Dakota State University, Madison, SD, USA","institution_ids":["https://openalex.org/I125467818"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I125467818"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":1.336,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.81344613,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":"13","issue":null,"first_page":"142990","last_page":"142997"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.8677999973297119,"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.8677999973297119,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.8604999780654907,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.835099995136261,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.766118049621582},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5084582567214966},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.4425336718559265},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3433249592781067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3407357931137085},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.11463192105293274},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.09248492121696472}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.766118049621582},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5084582567214966},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4425336718559265},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3433249592781067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3407357931137085},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11463192105293274},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.09248492121696472},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3587104","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3587104","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:d6d0f9cd3eb3439a9478711f3890e318","is_oa":true,"landing_page_url":"https://doaj.org/article/d6d0f9cd3eb3439a9478711f3890e318","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 142990-142997 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3587104","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3587104","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1967471703","https://openalex.org/W2098456636","https://openalex.org/W2963935794","https://openalex.org/W3043641306","https://openalex.org/W3086481683","https://openalex.org/W3114760331","https://openalex.org/W3130011944","https://openalex.org/W3142903977","https://openalex.org/W3152266692","https://openalex.org/W3195857585","https://openalex.org/W4224246371","https://openalex.org/W4281808401","https://openalex.org/W4306145873","https://openalex.org/W4394995399","https://openalex.org/W4397032804","https://openalex.org/W4403334193","https://openalex.org/W6752526365","https://openalex.org/W6775565728","https://openalex.org/W6786116758","https://openalex.org/W6790588633","https://openalex.org/W6840263849","https://openalex.org/W6856606227","https://openalex.org/W6864870587","https://openalex.org/W6871461881"],"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/W2163672025","https://openalex.org/W2048831961","https://openalex.org/W1606349578","https://openalex.org/W4399567378"],"abstract_inverted_index":{"This":[0,29],"paper":[1],"compares":[2],"synthetic":[3,113,135],"and":[4,21,69,108,114,126,130,151],"real-world":[5,81,115,144],"code":[6,20,59,116],"datasets":[7,155],"for":[8,50,123,156],"machine":[9,19,157],"learning":[10,158],"applications":[11,159],"in":[12,160],"cybersecurity":[13],"by":[14],"examining":[15],"the":[16,58,74,131],"relationships":[17],"between":[18],"Low-Level":[22],"Virtual":[23],"Machine":[24],"Intermediate":[25],"Representation":[26],"(LLVM":[27],"IR).":[28],"study":[30],"analyzes":[31],"1000":[32,41],"randomly":[33,42],"generated":[34,60],"programs":[35],"from":[36,45],"a":[37],"compiler":[38],"fuzzer":[39],"against":[40],"selected":[43],"samples":[44],"AnghaBench":[46],"to":[47,80,111],"evaluate":[48],"suitability":[49],"security":[51,149],"analysis":[52,55,128],"tasks.":[53],"Statistical":[54],"revealed":[56],"that":[57,134],"with":[61,83],"fuzzers":[62],"consistently":[63],"produces":[64],"more":[65],"complex":[66],"instruction":[67,76,102],"patterns":[68],"achieves":[70],"broader":[71],"coverage":[72,104],"of":[73],"available":[75],"sets,":[77],"when":[78],"compared":[79],"samples,":[82],"statistically":[84],"significant":[85],"differences":[86],"across":[87],"all":[88],"measured":[89],"categories":[90],"(<inline-formula":[91],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[92],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[93],"<tex-math":[94],"notation=\"LaTeX\">$p":[95],"\\lt":[96],"0.001$":[97],"</tex-math></inline-formula>).":[98],"The":[99],"research":[100,132],"examines":[101],"distributions,":[103],"metrics,":[105],"program":[106],"complexity,":[107],"statistical":[109],"properties":[110],"characterize":[112],"differences.":[117],"Our":[118],"findings":[119],"have":[120],"important":[121],"implications":[122],"vulnerability":[124],"detection":[125],"malware":[127],"systems,":[129],"shows":[133],"data":[136],"generation":[137],"can":[138],"effectively":[139],"complement":[140],"or":[141],"potentially":[142],"surpass":[143],"samples.":[145],"These":[146],"insights":[147],"help":[148],"researchers":[150],"practitioners":[152],"select":[153],"training":[154],"cybersecurity.":[161]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-09T07:52:08.696243","created_date":"2025-10-10T00:00:00"}