{"id":"https://openalex.org/W7116875605","doi":"https://doi.org/10.1109/itnac66378.2025.11302633","title":"A Review of the Use of Large Language Models to Generate Synthetic Cybersecurity Datasets","display_name":"A Review of the Use of Large Language Models to Generate Synthetic Cybersecurity Datasets","publication_year":2025,"publication_date":"2025-11-26","ids":{"openalex":"https://openalex.org/W7116875605","doi":"https://doi.org/10.1109/itnac66378.2025.11302633"},"language":null,"primary_location":{"id":"doi:10.1109/itnac66378.2025.11302633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itnac66378.2025.11302633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Telecommunication Networks and Applications Conference (ITNAC)","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/A5121117805","display_name":"Jack Gadsby","orcid":null},"institutions":[{"id":"https://openalex.org/I74899385","display_name":"Central Queensland University","ror":"https://ror.org/023q4bk22","country_code":"AU","type":"education","lineage":["https://openalex.org/I74899385"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Jack Gadsby","raw_affiliation_strings":["CQUniversity,School of Engineering &#x0026; Technology,Rockhampton North,QLD,Australia,4701"],"affiliations":[{"raw_affiliation_string":"CQUniversity,School of Engineering &#x0026; Technology,Rockhampton North,QLD,Australia,4701","institution_ids":["https://openalex.org/I74899385"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120322838","display_name":"Fariza Sabrina","orcid":null},"institutions":[{"id":"https://openalex.org/I74899385","display_name":"Central Queensland University","ror":"https://ror.org/023q4bk22","country_code":"AU","type":"education","lineage":["https://openalex.org/I74899385"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Fariza Sabrina","raw_affiliation_strings":["CQUniversity,School of Engineering &#x0026; Technology,Rockhampton North,QLD,Australia,4701"],"affiliations":[{"raw_affiliation_string":"CQUniversity,School of Engineering &#x0026; Technology,Rockhampton North,QLD,Australia,4701","institution_ids":["https://openalex.org/I74899385"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5121117805"],"corresponding_institution_ids":["https://openalex.org/I74899385"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.76333784,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.3889000117778778,"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/T11644","display_name":"Spam and Phishing Detection","score":0.3889000117778778,"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/T12519","display_name":"Cybercrime and Law Enforcement Studies","score":0.2614000141620636,"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/T10734","display_name":"Information and Cyber Security","score":0.033900000154972076,"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/metadata","display_name":"Metadata","score":0.633899986743927},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5223000049591064},{"id":"https://openalex.org/keywords/phishing","display_name":"Phishing","score":0.5072000026702881},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5049999952316284},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4652999937534332},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.3230000138282776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7139000296592712},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.633899986743927},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.5846999883651733},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5223000049591064},{"id":"https://openalex.org/C83860907","wikidata":"https://www.wikidata.org/wiki/Q135005","display_name":"Phishing","level":3,"score":0.5072000026702881},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5049999952316284},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.46619999408721924},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3073999881744385},{"id":"https://openalex.org/C2780264999","wikidata":"https://www.wikidata.org/wiki/Q7445032","display_name":"Security domain","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itnac66378.2025.11302633","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itnac66378.2025.11302633","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Telecommunication Networks and Applications Conference (ITNAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4018189311027527,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1991210879","https://openalex.org/W2924689635","https://openalex.org/W2964082408","https://openalex.org/W3119943161","https://openalex.org/W3201886739","https://openalex.org/W3212703167","https://openalex.org/W4206069908","https://openalex.org/W4379259169","https://openalex.org/W4387757573","https://openalex.org/W4388923662","https://openalex.org/W4389524555","https://openalex.org/W4390741016","https://openalex.org/W4392667162","https://openalex.org/W4392902389","https://openalex.org/W4399338566","https://openalex.org/W4399412887","https://openalex.org/W4402230126","https://openalex.org/W4402672281","https://openalex.org/W4405682757","https://openalex.org/W4406236959","https://openalex.org/W4407163436","https://openalex.org/W4407832462","https://openalex.org/W4409382496","https://openalex.org/W4411285020","https://openalex.org/W4411403346","https://openalex.org/W4414594130","https://openalex.org/W4416028946","https://openalex.org/W4416037229"],"related_works":[],"abstract_inverted_index":{"Access":[0],"to":[1,25,78,115],"high-quality,":[2],"realistic":[3],"datasets":[4],"is":[5,13],"critical":[6],"for":[7,47,74,92,130],"cybersecurity":[8,50,86,116,134],"research,":[9],"however":[10],"real-world":[11],"data":[12,72,107],"often":[14],"constrained":[15],"by":[16],"privacy,":[17],"classification,":[18],"and":[19,65,105,126,143],"legal":[20],"restrictions.":[21],"These":[22,109],"limitations":[23],"contribute":[24],"the":[26,39,69,84,124],"outdated,":[27],"imbalanced,":[28],"or":[29],"limited":[30,106],"realism":[31],"of":[32,42],"widely":[33],"available":[34],"datasets.":[35,59,117],"This":[36,118],"paper":[37],"reviews":[38],"emerging":[40],"use":[41],"LLMs":[43,88,132],"as":[44,68,100],"a":[45,53],"mechanism":[46],"generating":[48,93],"synthetic":[49],"data,":[51],"with":[52],"particular":[54],"emphasis":[55],"on":[56],"augmenting":[57],"existing":[58],"The":[60],"review":[61,119],"identifies":[62,127],"phishing":[63],"emails":[64],"system":[66],"logs":[67],"most":[70],"suitable":[71],"types":[73],"LLM-driven":[75],"augmentation":[76],"due":[77],"their":[79],"structured,":[80],"textual":[81],"nature.":[82],"Outside":[83],"specific":[85],"domain,":[87],"have":[89],"demonstrated":[90],"aptitude":[91],"realistic,":[94],"label-rich":[95],"artefacts,":[96],"addressing":[97],"challenges":[98],"such":[99],"class":[101],"imbalance,":[102],"labelling":[103],"inconsistency,":[104],"diversity.":[108],"capabilities":[110],"could":[111],"be":[112],"readily":[113],"applied":[114],"consolidates":[120],"key":[121],"studies":[122],"in":[123],"field":[125],"future":[128],"directions":[129],"integrating":[131],"into":[133],"dataset":[135],"pipelines,":[136],"particularly":[137],"through":[138],"automated":[139],"labelling,":[140],"metadata":[141],"enrichment,":[142],"hybrid":[144],"generative":[145],"architectures.":[146]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-12-23T00:00:00"}
