{"id":"https://openalex.org/W4388922130","doi":"https://doi.org/10.1109/bigdata59044.2023.10386735","title":"Toward training NLP models to take into account privacy leakages","display_name":"Toward training NLP models to take into account privacy leakages","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4388922130","doi":"https://doi.org/10.1109/bigdata59044.2023.10386735"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata59044.2023.10386735","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"preprint","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04299405/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092241331","display_name":"Gaspard Berthelier","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gaspard Berthelier","raw_affiliation_strings":["Université Paris Saclay,CentraleSupélec,Grenoble,France"],"affiliations":[{"raw_affiliation_string":"Université Paris Saclay,CentraleSupélec,Grenoble,France","institution_ids":["https://openalex.org/I4210107720"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108082107","display_name":"Antoine Boutet","orcid":null},"institutions":[{"id":"https://openalex.org/I48430043","display_name":"Institut National des Sciences Appliqu\u00e9es de Lyon","ror":"https://ror.org/050jn9y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I203339264","https://openalex.org/I48430043"]},{"id":"https://openalex.org/I100532134","display_name":"Universit\u00e9 Claude Bernard Lyon 1","ror":"https://ror.org/029brtt94","country_code":"FR","type":"education","lineage":["https://openalex.org/I100532134","https://openalex.org/I203339264"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Boutet","raw_affiliation_strings":["Univ Lyon, INSA Lyon, Inria, CITI, Lyon, France"],"affiliations":[{"raw_affiliation_string":"Univ Lyon, INSA Lyon, Inria, CITI, Lyon, France","institution_ids":["https://openalex.org/I48430043","https://openalex.org/I100532134"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090001513","display_name":"Antoine Richard","orcid":"https://orcid.org/0000-0001-8677-8910"},"institutions":[{"id":"https://openalex.org/I4210100596","display_name":"Hospices Civils de Lyon","ror":"https://ror.org/01502ca60","country_code":"FR","type":"healthcare","lineage":["https://openalex.org/I4210100596"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Antoine Richard","raw_affiliation_strings":["DSN Bron, Hospices Civil de Lyon, Grenoble, France"],"affiliations":[{"raw_affiliation_string":"DSN Bron, Hospices Civil de Lyon, Grenoble, France","institution_ids":["https://openalex.org/I4210100596"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":0,"max":68},"biblio":{"volume":null,"issue":null,"first_page":"4854","last_page":"4862"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9998,"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":0.9998,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9781,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9744,"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/differential-privacy","display_name":"Differential Privacy","score":0.60963583},{"id":"https://openalex.org/keywords/identification","display_name":"Identification","score":0.46629637},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named Entity Recognition","score":0.45180076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8241426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.70162326},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.68627846},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.61422},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.60963583},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.5823294},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.5093471},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47073734},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.46629637},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46493977},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.45180076},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4254038},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.42423147},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41839242},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38638037},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2551399},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.17987737},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11220434},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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}],"mesh":[],"locations_count":3,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata59044.2023.10386735","pdf_url":null,"source":{"id":"https://openalex.org/S4363607718","display_name":"2021 IEEE International Conference on Big Data (Big Data)","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":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hal.science/hal-04299405","pdf_url":"https://hal.science/hal-04299405/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://hal.science/hal-04299405/file/NLP_Privacy_Hopitaux%20%2818%29.pdf","pdf_url":"https://hal.science/hal-04299405/file/NLP_Privacy_Hopitaux%20%2818%29.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://hal.science/hal-04299405","pdf_url":"https://hal.science/hal-04299405/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":["Centre National de la Recherche Scientifique"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":28,"referenced_works":["https://openalex.org/W2473418344","https://openalex.org/W2535690855","https://openalex.org/W2896457183","https://openalex.org/W2965373594","https://openalex.org/W2971258845","https://openalex.org/W2978017171","https://openalex.org/W2986154550","https://openalex.org/W2990085462","https://openalex.org/W3010607409","https://openalex.org/W3012137864","https://openalex.org/W3112787034","https://openalex.org/W3153896080","https://openalex.org/W3163832451","https://openalex.org/W3165327186","https://openalex.org/W4221159672","https://openalex.org/W4226137521","https://openalex.org/W4283170666","https://openalex.org/W4287553002","https://openalex.org/W4288099476","https://openalex.org/W4296594784","https://openalex.org/W4318147454","https://openalex.org/W4318147820","https://openalex.org/W4318147821","https://openalex.org/W4320024104","https://openalex.org/W4376626934","https://openalex.org/W4385245566","https://openalex.org/W4385573947","https://openalex.org/W4392757531"],"related_works":["https://openalex.org/W4387517132","https://openalex.org/W4384133558","https://openalex.org/W4286970243","https://openalex.org/W3201448254","https://openalex.org/W3028847759","https://openalex.org/W3025615835","https://openalex.org/W2393688264","https://openalex.org/W2390660599","https://openalex.org/W2066431708","https://openalex.org/W173210993"],"abstract_inverted_index":{"With":[0,147],"the":[1,11,47,50,63,85,127,137,145,157,173,185,199,203],"rise":[2],"of":[3,13,33,65,87,188,201],"machine":[4],"learning":[5],"and":[6,36,60,118,160,169,197,206],"data-driven":[7],"models":[8,76,91,104,190],"especially":[9],"in":[10,74,81],"field":[12],"Natural":[14],"Language":[15],"Processing":[16],"(NLP),":[17],"a":[18,69,166,192],"strong":[19],"demand":[20],"for":[21,53],"sharing":[22],"data":[23,35,143,153,159],"between":[24],"organisations":[25],"has":[26,122],"emerged.":[27],"However":[28],"datasets":[29],"are":[30,57],"usually":[31],"composed":[32],"personal":[34],"thus":[37],"subject":[38],"to":[39,116,139,164,172],"numerous":[40],"regulations":[41],"which":[42,114,121],"require":[43],"anonymization":[44],"before":[45],"disseminating":[46],"data.":[48,108],"In":[49],"medical":[51,66,195],"domain":[52],"instance,":[54],"patient":[55],"records":[56],"extremely":[58],"sensitive":[59,107,119],"private,":[61],"but":[62,84],"de-identification":[64],"documents":[67],"is":[68,92],"complex":[70],"task.":[71],"Recent":[72],"advances":[73],"NLP":[75,103,189],"have":[77],"shown":[78],"encouraging":[79],"results":[80],"this":[82,95,148],"field,":[83],"question":[86],"whether":[88],"deploying":[89],"such":[90,177],"safe":[93],"remains.In":[94],"paper,":[96],"we":[97,110,150],"evaluate":[98,111,131],"three":[99],"privacy":[100,170,186],"risks":[101],"on":[102,106,126],"trained":[105],"Specifically,":[109],"counterfactual":[112],"memorization,":[113],"corresponds":[115],"rare":[117],"information":[120],"too":[123],"much":[124],"influence":[125],"model.":[128,146],"We":[129,182],"also":[130],"membership":[132],"inference":[133],"as":[134,136,178],"well":[135],"ability":[138],"extract":[140],"verbatim":[141],"training":[142,158],"from":[144,156],"evaluation,":[149],"can":[151],"cure":[152],"at":[154],"risk":[155],"calibrate":[161],"hyper":[162],"parameters":[163],"provide":[165],"supplementary":[167],"utility":[168],"trade-off":[171],"usual":[174],"mitigation":[175,207],"strategies":[176],"using":[179,194],"differential":[180],"privacy.":[181],"exhaustively":[183],"illustrate":[184],"leakage":[187],"through":[191],"use-case":[193],"texts":[196],"discuss":[198],"impact":[200],"both":[202],"proposed":[204],"methodology":[205],"schemes.":[208]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4388922130","counts_by_year":[],"updated_date":"2024-12-21T22:34:44.995589","created_date":"2023-11-23"}