{"id":"https://openalex.org/W4416935197","doi":"https://doi.org/10.1145/3786181.3788707","title":"The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable High-Accuracy Authorship Attribution","display_name":"The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable High-Accuracy Authorship Attribution","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W4416935197","doi":"https://doi.org/10.1145/3786181.3788707"},"language":"en","primary_location":{"id":"doi:10.1145/3786181.3788707","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786181.3788707","pdf_url":null,"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 3rd International Workshop on Large Language Models For Code","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3786181.3788707","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073042391","display_name":"Norbert Tihanyi","orcid":"https://orcid.org/0000-0002-9002-5935"},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]},{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE","HU"],"is_corresponding":false,"raw_author_name":"Norbert Tihanyi","raw_affiliation_strings":["Technology Innovation Institute, Abu Dhabi, United Arab Emirates and E\u00f6tv\u00f6s Lor\u00e1nd University, Budapest, Hungary"],"raw_orcid":"https://orcid.org/0000-0002-9002-5935","affiliations":[{"raw_affiliation_string":"Technology Innovation Institute, Abu Dhabi, United Arab Emirates and E\u00f6tv\u00f6s Lor\u00e1nd University, Budapest, Hungary","institution_ids":["https://openalex.org/I4210087059","https://openalex.org/I106118109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033900051","display_name":"Bilel Cherif","orcid":"https://orcid.org/0009-0006-0095-106X"},"institutions":[{"id":"https://openalex.org/I4210087059","display_name":"Technology Innovation Institute","ror":"https://ror.org/001kv2y39","country_code":"AE","type":"facility","lineage":["https://openalex.org/I4210087059"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Bilel Cherif","raw_affiliation_strings":["Technology Innovation Institute, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0009-0006-0095-106X","affiliations":[{"raw_affiliation_string":"Technology Innovation Institute, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210087059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114601640","display_name":"Richard A. Dubniczky","orcid":"https://orcid.org/0009-0003-3951-1932"},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Richard A. Dubniczky","raw_affiliation_strings":["E\u00f6tv\u00f6s Lor\u00e1nd University, Budapest, Hungary"],"raw_orcid":"https://orcid.org/0009-0003-3951-1932","affiliations":[{"raw_affiliation_string":"E\u00f6tv\u00f6s Lor\u00e1nd University, Budapest, Hungary","institution_ids":["https://openalex.org/I106118109"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026903935","display_name":"Mohamed Amine Ferrag","orcid":"https://orcid.org/0000-0002-0632-3172"},"institutions":[{"id":"https://openalex.org/I201726411","display_name":"United Arab Emirates University","ror":"https://ror.org/01km6p862","country_code":"AE","type":"education","lineage":["https://openalex.org/I201726411"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Mohamed Amine Ferrag","raw_affiliation_strings":["United Arab Emirates University, Abu Dhabi, United Arab Emirates"],"raw_orcid":"https://orcid.org/0000-0002-0632-3172","affiliations":[{"raw_affiliation_string":"United Arab Emirates University, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I201726411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052473439","display_name":"Tam\u00e1s Bisztray","orcid":"https://orcid.org/0000-0003-2626-3434"},"institutions":[{"id":"https://openalex.org/I106118109","display_name":"E\u00f6tv\u00f6s Lor\u00e1nd University","ror":"https://ror.org/01jsq2704","country_code":"HU","type":"education","lineage":["https://openalex.org/I106118109"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Lajos Balkanyi","raw_affiliation_strings":["E\u00f6tv\u00f6s Lor\u00e1nd University, Budapest, Hungary"],"raw_orcid":"https://orcid.org/0009-0004-2316-4806","affiliations":[{"raw_affiliation_string":"E\u00f6tv\u00f6s Lor\u00e1nd University, Budapest, Hungary","institution_ids":["https://openalex.org/I106118109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052473439","display_name":"Tam\u00e1s Bisztray","orcid":"https://orcid.org/0000-0003-2626-3434"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Tamas Bisztray","raw_affiliation_strings":["University of Oslo, Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0003-2626-3434","affiliations":[{"raw_affiliation_string":"University of Oslo, Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0219337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"42","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.8761000037193298,"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"}},"topics":[{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.8761000037193298,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.04769999906420708,"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/T11644","display_name":"Spam and Phishing Detection","score":0.011099999770522118,"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/authorship-attribution","display_name":"Authorship attribution","score":0.6730999946594238},{"id":"https://openalex.org/keywords/flagging","display_name":"Flagging","score":0.5727999806404114},{"id":"https://openalex.org/keywords/javascript","display_name":"JavaScript","score":0.5238000154495239},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4560999870300293},{"id":"https://openalex.org/keywords/attribution","display_name":"Attribution","score":0.43299999833106995},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3993000090122223},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.3944999873638153},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.39169999957084656}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7457000017166138},{"id":"https://openalex.org/C3020202489","wikidata":"https://www.wikidata.org/wiki/Q2032038","display_name":"Authorship attribution","level":2,"score":0.6730999946594238},{"id":"https://openalex.org/C2777548347","wikidata":"https://www.wikidata.org/wiki/Q5456937","display_name":"Flagging","level":2,"score":0.5727999806404114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5662999749183655},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5605999827384949},{"id":"https://openalex.org/C544833334","wikidata":"https://www.wikidata.org/wiki/Q2005","display_name":"JavaScript","level":2,"score":0.5238000154495239},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4560999870300293},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.43299999833106995},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3880999982357025},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.31360000371932983},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.28769999742507935},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2644999921321869},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C2385561","wikidata":"https://www.wikidata.org/wiki/Q45432","display_name":"RSS","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3786181.3788707","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786181.3788707","pdf_url":null,"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 3rd International Workshop on Large Language Models For Code","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.10493","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.10493","pdf_url":"https://arxiv.org/pdf/2510.10493","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.10493","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.10493","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3786181.3788707","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786181.3788707","pdf_url":null,"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 3rd International Workshop on Large Language Models For Code","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,99],"paper,":[2],"we":[3,101,166],"present":[4],"the":[5,35,38,53,141,168],"first":[6],"large-scale":[7],"study":[8],"exploring":[9],"whether":[10],"JavaScript":[11,86],"code":[12,131],"generated":[13],"by":[14],"Large":[15],"Language":[16],"Models":[17],"(LLMs)":[18],"contains":[19],"distinguishable":[20],"fingerprints":[21,146],"enabling":[22],"reliable":[23],"model":[24,40,142],"attribution.":[25],"As":[26],"developers":[27],"increasingly":[28],"rely":[29],"on":[30,112,117,129,174],"third-party":[31],"AI":[32],"aggregators,":[33],"verifying":[34],"identity":[36],"of":[37,62],"serving":[39],"is":[41],"critical":[42],"for":[43,95],"vulnerability":[44],"detection,":[45],"API":[46],"integrity":[47],"and":[48,78,89,115,123,172],"detecting":[49],"model-routing":[50],"discrepancies":[51],"in":[52],"software":[54],"supply":[55],"chain.":[56],"We":[57,152],"introduce":[58],"LLM-NodeJS,":[59],"a":[60,104,134],"dataset":[61],"50,000":[63],"Node.js":[64],"back-end":[65],"programs":[66],"from":[67],"20":[68],"large":[69],"language":[70],"models.":[71],"For":[72],"each":[73],"code,":[74],"minified,":[75],"mangled,":[76],"obfuscated":[77],"deobfuscated":[79],"versions":[80,91],"are":[81,92],"created":[82],"yielding":[83],"250,000":[84],"unique":[85],"samples.":[87],"JSIR":[88],"AST":[90],"also":[93],"added":[94],"further":[96,153],"research.":[97],"Using":[98],"dataset,":[100,169],"propose":[102],"CodeT5-JSA,":[103],"custom":[105],"encoder-only":[106],"architecture":[107],"that":[108,140,155],"achieves":[109],"95.8%":[110],"accuracy":[111],"five-class":[113],"attribution":[114],"88.5%":[116],"twenty-class":[118],"tasks,":[119],"significantly":[120],"outperforming":[121],"BERT":[122],"CodeBERT":[124],"baselines.":[125],"Crucially,":[126],"our":[127],"evaluation":[128],"unseen":[130],"shows":[132],"only":[133],"marginal":[135],"3\u20136%":[136],"performance":[137],"drop,":[138],"confirming":[139],"captures":[143],"persistent":[144],"structural":[145,157],"rather":[147],"than":[148],"memorizing":[149],"task-specific":[150],"patterns.":[151],"demonstrate":[154],"these":[156],"signals":[158],"survive":[159],"aggressive":[160],"obfuscation.":[161],"To":[162],"support":[163],"open":[164],"science,":[165],"release":[167],"training":[170],"scripts,":[171],"models":[173],"GitHub:":[175],"https://github.com/LLM-NodeJS-dataset.":[176]},"counts_by_year":[],"updated_date":"2026-07-09T05:49:46.723101","created_date":"2025-10-15T00:00:00"}