{"id":"https://openalex.org/W4404002909","doi":"https://doi.org/10.1145/3702980","title":"Trained without My Consent: Detecting Code Inclusion in Language Models Trained on Code","display_name":"Trained without My Consent: Detecting Code Inclusion in Language Models Trained on Code","publication_year":2024,"publication_date":"2024-11-02","ids":{"openalex":"https://openalex.org/W4404002909","doi":"https://doi.org/10.1145/3702980"},"language":"en","primary_location":{"id":"doi:10.1145/3702980","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3702980","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3702980","source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3702980","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076505896","display_name":"Vahid Majdinasab","orcid":"https://orcid.org/0000-0003-4411-0810"},"institutions":[{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vahid Majdinasab","raw_affiliation_strings":["Polytechnique Montreal, Montreal, Quebec, Canada","Polytechnique Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0003-4411-0810","affiliations":[{"raw_affiliation_string":"Polytechnique Montreal, Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I45683168"]},{"raw_affiliation_string":"Polytechnique Montreal, Canada","institution_ids":["https://openalex.org/I45683168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079607563","display_name":"Amin Nikanjam","orcid":"https://orcid.org/0000-0002-0440-6839"},"institutions":[{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Amin Nikanjam","raw_affiliation_strings":["Polytechnique Montreal, Montreal, Quebec, Canada","Polytechnique Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0002-0440-6839","affiliations":[{"raw_affiliation_string":"Polytechnique Montreal, Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I45683168"]},{"raw_affiliation_string":"Polytechnique Montreal, Canada","institution_ids":["https://openalex.org/I45683168"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071052367","display_name":"Foutse Khomh","orcid":"https://orcid.org/0000-0002-5704-4173"},"institutions":[{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Foutse Khomh","raw_affiliation_strings":["Polytechnique Montreal, Montreal, Quebec, Canada","Polytechnique Montreal, Canada"],"raw_orcid":"https://orcid.org/0000-0002-5704-4173","affiliations":[{"raw_affiliation_string":"Polytechnique Montreal, Montreal, Quebec, Canada","institution_ids":["https://openalex.org/I45683168"]},{"raw_affiliation_string":"Polytechnique Montreal, Canada","institution_ids":["https://openalex.org/I45683168"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45683168"],"apc_list":null,"apc_paid":null,"fwci":1.3892,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.84532758,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"34","issue":"4","first_page":"1","last_page":"46"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9977999925613403,"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/T10028","display_name":"Topic Modeling","score":0.9977999925613403,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9957000017166138,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9937999844551086,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5968852639198303},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5335450768470764},{"id":"https://openalex.org/keywords/inclusion","display_name":"Inclusion (mineral)","score":0.49633461236953735},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.42504462599754333},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.16984698176383972}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5968852639198303},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5335450768470764},{"id":"https://openalex.org/C109359841","wikidata":"https://www.wikidata.org/wiki/Q728944","display_name":"Inclusion (mineral)","level":2,"score":0.49633461236953735},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.42504462599754333},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.16984698176383972},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3702980","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3702980","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3702980","source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},{"id":"pmh:oai:publications.polymtl.ca:59858","is_oa":false,"landing_page_url":"https://publications.polymtl.ca/59858/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401013","display_name":"PolyPublie (\u00c9cole Polytechnique de Montr\u00e9al)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45683168","host_organization_name":"Polytechnique Montr\u00e9al","host_organization_lineage":["https://openalex.org/I45683168"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article de revue"}],"best_oa_location":{"id":"doi:10.1145/3702980","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3702980","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3702980","source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320331165","display_name":"Fonds de recherche du Qu\u00e9bec","ror":"https://ror.org/00w3qhf76"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404002909.pdf"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1555168845","https://openalex.org/W1647671624","https://openalex.org/W1967995512","https://openalex.org/W2090398160","https://openalex.org/W2101832700","https://openalex.org/W2119821925","https://openalex.org/W2165739648","https://openalex.org/W2298313545","https://openalex.org/W2517358422","https://openalex.org/W2528747608","https://openalex.org/W2535690855","https://openalex.org/W2566079294","https://openalex.org/W2747692572","https://openalex.org/W2761145057","https://openalex.org/W2769811094","https://openalex.org/W2806530724","https://openalex.org/W2911915417","https://openalex.org/W2913100656","https://openalex.org/W2919115771","https://openalex.org/W2945440850","https://openalex.org/W2955426500","https://openalex.org/W2955439455","https://openalex.org/W2962739339","https://openalex.org/W2963378725","https://openalex.org/W2963456518","https://openalex.org/W2970476646","https://openalex.org/W2983140679","https://openalex.org/W3007252788","https://openalex.org/W3011574394","https://openalex.org/W3014581084","https://openalex.org/W3043761819","https://openalex.org/W3045279034","https://openalex.org/W3081886688","https://openalex.org/W3085162807","https://openalex.org/W3088409176","https://openalex.org/W3089515198","https://openalex.org/W3102825217","https://openalex.org/W3112689365","https://openalex.org/W3115042282","https://openalex.org/W3138758728","https://openalex.org/W3138815606","https://openalex.org/W3155297957","https://openalex.org/W3158803559","https://openalex.org/W3201892058","https://openalex.org/W4226137521","https://openalex.org/W4281483318","https://openalex.org/W4285325543","https://openalex.org/W4292014584","https://openalex.org/W4297957988","https://openalex.org/W4301168982","https://openalex.org/W4312565886","https://openalex.org/W4321500271","https://openalex.org/W4322766882","https://openalex.org/W4380993527","https://openalex.org/W4389518760","https://openalex.org/W4389519044","https://openalex.org/W4403761251","https://openalex.org/W4404781336","https://openalex.org/W6681648988","https://openalex.org/W6853251322","https://openalex.org/W6853579704"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3185553570","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Code":[0],"auditing":[1,78,242],"ensures":[2],"that":[3,16,106,190,199,237],"the":[4,37,62,75,113,120,123,208,241],"developed":[5,80],"code":[6,21,45,79,130,160,183,253],"adheres":[7],"to":[8,89,112,174,177,202,222,233],"standards,":[9],"regulations,":[10],"and":[11,151,170],"copyright":[12,137],"protection":[13],"by":[14],"verifying":[15],"it":[17,86],"does":[18],"not":[19,109],"contain":[20],"from":[22,56],"protected":[23],"sources.":[24,59],"The":[25,47],"recent":[26],"advent":[27],"of":[28,64,116,122,194,197,217,244,252],"Large":[29],"Language":[30],"Models":[31],"(LLMs)":[32],"as":[33,68,85,129],"coding":[34],"assistants":[35],"in":[36,74,162,231],"software":[38],"development":[39,97],"process":[40,243],"poses":[41],"new":[42,146],"challenges":[43],"for":[44,49,135,158,181],"auditing.":[46],"dataset":[48],"training":[50,114,124,165],"these":[51,117],"models":[52],"is":[53,83,87,192,214,238],"mainly":[54],"collected":[55],"publicly":[57],"available":[58],"This":[60],"raises":[61],"issue":[63],"intellectual":[65],"property":[66],"infringement":[67],"developers\u2019":[69],"codes":[70,198],"are":[71,133],"already":[72],"included":[73],"dataset.":[76,166],"Therefore,":[77],"using":[81],"LLMs":[82],"challenging,":[84],"difficult":[88],"reliably":[90],"assert":[91],"if":[92],"an":[93,163,204],"LLM":[94],"used":[95,201],"during":[96,240],"has":[98,227],"been":[99],"trained":[100],"on":[101,155],"specific":[102],"copyrighted":[103],"codes,":[104],"given":[105],"we":[107,143,188],"do":[108],"have":[110],"access":[111],"datasets":[115],"models.":[118],"Given":[119],"non-disclosure":[121],"datasets,":[125],"traditional":[126],"approaches":[127],"such":[128],"clone":[131,210,235],"detection":[132,211,236],"insufficient":[134],"asserting":[136],"infringement.":[138],"To":[139],"address":[140],"this":[141],"challenge,":[142],"propose":[144],"a":[145,149,179],"approach,":[147],"TraWiC;":[148],"model-agnostic":[150],"interpretable":[152],"method":[153],"based":[154],"membership":[156],"inference":[157],"detecting":[159,182,195,218],"inclusion":[161],"LLM\u2019s":[164],"We":[167],"extract":[168],"syntactic":[169],"semantic":[171],"identifiers":[172],"unique":[173],"each":[175],"program":[176],"train":[178,203],"classifier":[180],"inclusion.":[184],"In":[185,206,220],"our":[186],"experiments,":[187],"observe":[189],"TraWiC":[191,226],"capable":[193,216],"83.87%":[196],"were":[200],"LLM.":[205],"comparison,":[207],"prevalent":[209],"tool":[212],"NiCad":[213],"only":[215],"47.64%.":[219],"addition":[221],"its":[223],"remarkable":[224],"performance,":[225],"low":[228],"resource":[229],"overhead":[230],"contrast":[232],"pairwise":[234],"conducted":[239],"tools":[245],"like":[246],"CodeWhisperer":[247],"reference":[248],"tracker,":[249],"across":[250],"thousands":[251],"snippets.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2024-11-03T00:00:00"}