{"id":"https://openalex.org/W2952604841","doi":"https://doi.org/10.1145/3292500.3330885","title":"Auditing Data Provenance in Text-Generation Models","display_name":"Auditing Data Provenance in Text-Generation Models","publication_year":2019,"publication_date":"2019-07-25","ids":{"openalex":"https://openalex.org/W2952604841","doi":"https://doi.org/10.1145/3292500.3330885","mag":"2952604841"},"language":"en","primary_location":{"id":"doi:10.1145/3292500.3330885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330885","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330885","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","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/10.1145/3292500.3330885","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048446895","display_name":"Congzheng Song","orcid":"https://orcid.org/0000-0002-5076-7299"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Congzheng Song","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038206174","display_name":"Vitaly Shmatikov","orcid":"https://orcid.org/0009-0002-1336-5714"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vitaly Shmatikov","raw_affiliation_strings":["Cornell Tech, New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell Tech, New York, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5048446895"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":13.8726,"has_fulltext":false,"cited_by_count":183,"citation_normalized_percentile":{"value":0.99057435,"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":"196","last_page":"206"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9994000196456909,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9973999857902527,"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/T12034","display_name":"Digital and Cyber Forensics","score":0.9962000250816345,"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":0.8543351888656616},{"id":"https://openalex.org/keywords/audit","display_name":"Audit","score":0.7467485070228577},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.7227537035942078},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6333540081977844},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.6088579893112183},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5614228844642639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49811649322509766},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4632386565208435},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45135462284088135},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.450337678194046},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4361421465873718},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.41594916582107544},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34428369998931885},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33451515436172485},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.24499082565307617},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.17193612456321716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8543351888656616},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.7467485070228577},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.7227537035942078},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6333540081977844},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.6088579893112183},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5614228844642639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49811649322509766},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4632386565208435},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45135462284088135},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.450337678194046},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4361421465873718},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.41594916582107544},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34428369998931885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33451515436172485},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.24499082565307617},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.17193612456321716},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3292500.3330885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330885","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330885","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3292500.3330885","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3292500.3330885","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3292500.3330885","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G1044999958","display_name":null,"funder_award_id":"1611770","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2952604841.pdf","grobid_xml":"https://content.openalex.org/works/W2952604841.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W1522301498","https://openalex.org/W1591706642","https://openalex.org/W2040228409","https://openalex.org/W2064675550","https://openalex.org/W2118585731","https://openalex.org/W2119804197","https://openalex.org/W2125320996","https://openalex.org/W2157331557","https://openalex.org/W2198253679","https://openalex.org/W2250660307","https://openalex.org/W2525778437","https://openalex.org/W2535690855","https://openalex.org/W2541884796","https://openalex.org/W2740919303","https://openalex.org/W2757528734","https://openalex.org/W2765308317","https://openalex.org/W2766255512","https://openalex.org/W2785648721","https://openalex.org/W2786233556","https://openalex.org/W2788502731","https://openalex.org/W2795435272","https://openalex.org/W2798657499","https://openalex.org/W2798878995","https://openalex.org/W2884280357","https://openalex.org/W2887995258","https://openalex.org/W2949780682","https://openalex.org/W2953384591","https://openalex.org/W2962854379","https://openalex.org/W2963825865","https://openalex.org/W2964116855","https://openalex.org/W2964151798","https://openalex.org/W2964352131","https://openalex.org/W3023001449","https://openalex.org/W3137695714"],"related_works":["https://openalex.org/W2098987383","https://openalex.org/W2417260800","https://openalex.org/W1596203174","https://openalex.org/W2117933979","https://openalex.org/W2283130723","https://openalex.org/W103938586","https://openalex.org/W2104718772","https://openalex.org/W2980207396","https://openalex.org/W3156493709","https://openalex.org/W3029990846"],"abstract_inverted_index":{"To":[0],"help":[1],"enforce":[2],"data-protection":[3],"regulations":[4],"such":[5,70],"as":[6,71],"GDPR":[7],"and":[8,50,63,76,80,139],"detect":[9],"unauthorized":[10],"uses":[11],"of":[12,59,108],"personal":[13,68],"data,":[14],"we":[15],"develop":[16],"a":[17,33,82,94,97],"new":[18],"model":[19],"auditing":[20,40,84],"technique":[21],"that":[22,43,86,114,122],"helps":[23],"users":[24],"check":[25],"if":[26,96],"their":[27],"data":[28,69],"was":[29],"used":[30,102],"to":[31,93,103,126,147],"train":[32,104],"machine":[34],"learning":[35],"model.":[36],"We":[37,78,111,130],"focus":[38],"on":[39,67],"deep-learning":[41],"models":[42,54,121,135],"generate":[44],"natural-language":[45],"text,":[46],"including":[47],"word":[48,137],"prediction":[49],"dialog":[51],"generation.":[52],"These":[53],"are":[55,64,123],"at":[56],"the":[57,127],"core":[58],"popular":[60],"online":[61],"services":[62],"often":[65],"trained":[66],"users'":[72],"messages,":[73],"searches,":[74],"chats,":[75],"comments.":[77],"design":[79],"evaluate":[81],"black-box":[83],"method":[85,116],"can":[87,117],"detect,":[88],"with":[89],"very":[90],"few":[91],"queries":[92],"model,":[95],"particular":[98],"user's":[99],"texts":[100],"were":[101],"it":[105],"(among":[106],"thousands":[107],"other":[109],"users).":[110],"empirically":[112],"show":[113],"our":[115],"successfully":[118],"audit":[119],"well-generalized":[120],"not":[124],"overfitted":[125],"training":[128],"data.":[129],"also":[131],"analyze":[132],"how":[133],"text-generation":[134],"memorize":[136],"sequences":[138],"explain":[140],"why":[141],"this":[142],"memorization":[143],"makes":[144],"them":[145],"amenable":[146],"auditing.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":32},{"year":2022,"cited_by_count":34},{"year":2021,"cited_by_count":35},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}