{"id":"https://openalex.org/W3099692016","doi":"https://doi.org/10.18653/v1/2020.privatenlp-1.2","title":"A Differentially Private Text Perturbation Method Using Regularized Mahalanobis Metric","display_name":"A Differentially Private Text Perturbation Method Using Regularized Mahalanobis Metric","alternate_titles":[],"publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3099692016","doi":"https://doi.org/10.18653/v1/2020.privatenlp-1.2","mag":"3099692016"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.privatenlp-1.2","doi":"https://doi.org/10.18653/v1/2020.privatenlp-1.2","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.privatenlp-1.2","pdf_url":"https://www.aclweb.org/anthology/2020.privatenlp-1.2.pdf","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 Second Workshop on Privacy in NLP","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W3099692016"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/2020.privatenlp-1.2.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101666776","display_name":"Zekun Xu","orcid":"https://orcid.org/0000-0002-1968-7100","observed_orcids":["https://orcid.org/0000-0002-1968-7100","https://orcid.org/0000-0003-1786-078X"]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Zekun Xu","raw_affiliation_strings":["Amazon Arlington, VA USA","Amazon Seattle, WA USA","Oluwaseyi Feyisetan Amazon Seattle, WA USA","Seattle, WA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Arlington, VA USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Seattle, WA USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Oluwaseyi Feyisetan Amazon Seattle, WA USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Seattle, WA USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104083401","display_name":"Abhinav Aggarwal","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Abhinav Aggarwal","raw_affiliation_strings":["Amazon Seattle, WA USA","Amazon Arlington, VA USA","Oluwaseyi Feyisetan Amazon Seattle, WA USA","Seattle, WA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Seattle, WA USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Arlington, VA USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Oluwaseyi Feyisetan Amazon Seattle, WA USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Seattle, WA USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021612761","display_name":"Oluwaseyi Feyisetan","orcid":"https://orcid.org/0000-0002-0786-9505","observed_orcids":["https://orcid.org/0000-0002-0786-9505"]},"institutions":[],"countries":[],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Oluwaseyi Feyisetan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5070387976","display_name":"Nathanael Teissier","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Nathanael Teissier","raw_affiliation_strings":["Amazon Arlington, VA USA","Oluwaseyi Feyisetan Amazon Seattle, WA USA","Amazon Seattle, WA USA","Seattle, WA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Arlington, VA USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Oluwaseyi Feyisetan Amazon Seattle, WA USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Amazon Seattle, WA USA","institution_ids":["https://openalex.org/I1311688040"]},{"raw_affiliation_string":"Seattle, WA USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5196,"has_fulltext":true,"cited_by_count":60,"citation_normalized_percentile":{"value":0.8658133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7","last_page":"17"},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":1.0,"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":1.0,"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/T11045","display_name":"Privacy, Security, and Data Protection","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10237","display_name":"Cryptography and Data Security","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9010000228881836},{"id":"https://openalex.org/keywords/text-perturbation","display_name":"text perturbation","score":0.9940000176429749},{"id":"https://openalex.org/keywords/mahalanobis-metric","display_name":"Mahalanobis metric","score":0.9179999828338623},{"id":"https://openalex.org/keywords/privacy-utility-trade-off","display_name":"privacy-utility trade-off","score":0.8339999914169312},{"id":"https://openalex.org/keywords/noise-injection","display_name":"noise injection","score":0.6489999890327454},{"id":"https://openalex.org/keywords/word-embeddings","display_name":"word embeddings","score":0.6679999828338623}],"concepts":[{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.7036574482917786},{"id":"https://openalex.org/C1921717","wikidata":"https://www.wikidata.org/wiki/Q1334846","display_name":"Mahalanobis distance","level":2,"score":0.6958872675895691},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6469883918762207},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6169576644897461},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.4600711762905121},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.4517202079296112},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44456666707992554},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43990689516067505},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.4177469313144684},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.41002362966537476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3853462338447571},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34904590249061584},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3421463966369629},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3309438228607178},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12048417329788208},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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:10.18653/v1/2020.privatenlp-1.2","doi":"https://doi.org/10.18653/v1/2020.privatenlp-1.2","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.privatenlp-1.2","pdf_url":"https://www.aclweb.org/anthology/2020.privatenlp-1.2.pdf","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 Second Workshop on Privacy in NLP","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.privatenlp-1.2","doi":"https://doi.org/10.18653/v1/2020.privatenlp-1.2","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.privatenlp-1.2","pdf_url":"https://www.aclweb.org/anthology/2020.privatenlp-1.2.pdf","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 Second Workshop on Privacy in NLP","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3099692016.pdf","grobid_xml":"https://content.openalex.org/works/W3099692016.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W145956381","https://openalex.org/W331889179","https://openalex.org/W1540596182","https://openalex.org/W1658920975","https://openalex.org/W1690606251","https://openalex.org/W1711940457","https://openalex.org/W1873763122","https://openalex.org/W1904610397","https://openalex.org/W1975937116","https://openalex.org/W1989021088","https://openalex.org/W1990512452","https://openalex.org/W1996118086","https://openalex.org/W2026002400","https://openalex.org/W2027595342","https://openalex.org/W2036166268","https://openalex.org/W2040228409","https://openalex.org/W2056700697","https://openalex.org/W2062112832","https://openalex.org/W2082894754","https://openalex.org/W2095272373","https://openalex.org/W2106139345","https://openalex.org/W2109426455","https://openalex.org/W2115972246","https://openalex.org/W2116950384","https://openalex.org/W2124090777","https://openalex.org/W2135930857","https://openalex.org/W2181631377","https://openalex.org/W2188999827","https://openalex.org/W2198253679","https://openalex.org/W2245160765","https://openalex.org/W2250539671","https://openalex.org/W2288752886","https://openalex.org/W2468328197","https://openalex.org/W2476457629","https://openalex.org/W2493916176","https://openalex.org/W2535690855","https://openalex.org/W2807096445","https://openalex.org/W2901147448","https://openalex.org/W2974738913","https://openalex.org/W2980848703","https://openalex.org/W2981248822","https://openalex.org/W3017286287","https://openalex.org/W3104360443","https://openalex.org/W3123972088","https://openalex.org/W4205228770","https://openalex.org/W4288345394"],"related_works":["https://openalex.org/W3094473903","https://openalex.org/W3185974173","https://openalex.org/W3116799215","https://openalex.org/W2980848703","https://openalex.org/W7127428585","https://openalex.org/W3173004511","https://openalex.org/W4385734328","https://openalex.org/W3113313887","https://openalex.org/W3164243831","https://openalex.org/W4385570555"],"abstract_inverted_index":{"Balancing":[0],"the":[1,56,62,66,72,85,92,95,101,115,136,156,160,165,174,177,187,211,216,224],"privacy-utility":[2],"tradeoff":[3],"is":[4,26,33,82,118],"a":[5,37,44,107,124,130,191],"crucial":[6],"requirement":[7],"of":[8,74,135,183,219],"many":[9],"practical":[10],"machine":[11],"learning":[12],"systems":[13],"that":[14,173,207],"deal":[15],"with":[16],"sensitive":[17],"customer":[18],"data.A":[19],"popular":[20],"approach":[21],"for":[22,91,155],"privacypreserving":[23],"text":[24,31,125],"analysis":[25],"noise":[27,46,87,116,145,152,166],"injection,":[28],"in":[29,94,100,106,159,164,176],"which":[30],"data":[32,81],"first":[34],"mapped":[35],"into":[36],"continuous":[38],"embedding":[39,102,161],"space,":[40],"perturbed":[41,80],"by":[42],"sampling":[43],"spherical":[45,86],"from":[47],"an":[48,150],"appropriate":[49],"distribution,":[50],"and":[51,198],"then":[52],"projected":[53],"back":[54],"to":[55,64,139,153,214,223],"discrete":[57],"vocabulary":[58],"space.While":[59],"this":[60,79,120,141,147,196],"allows":[61],"perturbation":[63,126],"admit":[65],"required":[67],"metric":[68,138,148,197],"differential":[69],"privacy,":[70],"often":[71],"utility":[73,220],"downstream":[75],"tasks":[76],"modeled":[77],"on":[78,129,195],"low":[83],"because":[84],"does":[88],"not":[89],"account":[90,154],"variability":[93],"density":[96],"around":[97],"different":[98,169],"words":[99,105,175],"space.In":[103],"particular,":[104],"sparse":[108,178],"region":[109,179],"are":[110],"likely":[111],"unchanged":[112],"even":[113],"when":[114],"scale":[117,167],"large.In":[119],"paper,":[121],"we":[122,204],"propose":[123],"mechanism":[127,209],"based":[128,194],"carefully":[131],"designed":[132],"regularized":[133],"variant":[134],"Mahalanobis":[137],"overcome":[140],"problem.For":[142],"any":[143],"given":[144],"scale,":[146],"adds":[149],"elliptical":[151],"covariance":[157],"structure":[158],"space.This":[162],"heterogeneity":[163],"along":[168],"directions":[170],"helps":[171],"ensure":[172],"have":[180],"sufficient":[181],"likelihood":[182],"replacement":[184],"without":[185],"sacrificing":[186],"overall":[188],"utility.We":[189],"provide":[190],"text-perturbation":[192],"algorithm":[193],"formally":[199],"prove":[200],"its":[201],"privacy":[202,212],"guarantees.Additionally,":[203],"empirically":[205],"show":[206],"our":[208],"improves":[210],"statistics":[213],"achieve":[215],"same":[217],"level":[218],"as":[221],"compared":[222],"state-of-the-art":[225],"Laplace":[226],"mechanism.":[227]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3099692016","counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":7}],"updated_date":"2026-11-20T13:11:24.684918","created_date":"2020-11-23T00:00:00"}
