{"id":"https://openalex.org/W4417026720","doi":"https://doi.org/10.1613/jair.1.21111","title":"How to DP-Fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy","display_name":"How to DP-Fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy","publication_year":2026,"publication_date":"2026-07-07","ids":{"openalex":"https://openalex.org/W4417026720","doi":"https://doi.org/10.1613/jair.1.21111"},"language":null,"primary_location":{"id":"doi:10.1613/jair.1.21111","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.21111","pdf_url":"https://jair.org/index.php/jair/article/download/21111/27321","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://jair.org/index.php/jair/article/download/21111/27321","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102899387","display_name":"Natalia Ponomareva","orcid":"https://orcid.org/0009-0005-6761-1468"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Natalia Ponomareva","raw_affiliation_strings":["a:1:{s:5:\"en_US\";s:6:\"Google\";}"],"raw_orcid":"https://orcid.org/0009-0005-6761-1468","affiliations":[{"raw_affiliation_string":"a:1:{s:5:\"en_US\";s:6:\"Google\";}","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413782","display_name":"Zheng Xu","orcid":"https://orcid.org/0000-0003-0648-0327"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng Xu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0003-6747-3953","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027716210","display_name":"H. Brendan McMahan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H. Brendan McMahan","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0003-5892-4193","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064699160","display_name":"Peter Kairouz","orcid":"https://orcid.org/0000-0001-6897-5937"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Kairouz","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6897-5937","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068868453","display_name":"Lucas Rosenblatt","orcid":"https://orcid.org/0000-0001-6952-4361"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lucas Rosenblatt","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074251728","display_name":"Vincent Cohen-Addad","orcid":"https://orcid.org/0000-0002-0779-8962"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Cohen-Addad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060428515","display_name":"Crist\u00f3bal Guzm\u00e1n","orcid":"https://orcid.org/0000-0002-1498-2055"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cristobal Guzman","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1498-2055","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080008812","display_name":"Ryan M. McKenna","orcid":"https://orcid.org/0000-0001-7335-2806"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryan McKenna","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4950-1952","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039644814","display_name":"Galen Andrew","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Galen Andrew","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0004-9804-7882","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056132034","display_name":"Alex Bie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Bie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019580477","display_name":"Dahua Yu","orcid":"https://orcid.org/0000-0001-7850-7512"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Da Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108686147","display_name":"\u0410.\u0412. \u041a\u0443\u0440\u0430\u043a\u0438\u043d","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Kurakin","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0008-5952-9394","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024817143","display_name":"Morteza Zadimoghaddam","orcid":"https://orcid.org/0000-0003-0717-1120"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Morteza Zadimoghaddam","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0717-1120","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070795618","display_name":"Sergei Vassilvitskii","orcid":"https://orcid.org/0000-0003-0235-1624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sergei Vassilvitskii","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0235-1624","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5103331911","display_name":"Andreas Terzis","orcid":"https://orcid.org/0000-0002-5681-3399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Terzis","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5681-3399","affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0192468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"86","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.7681000232696533,"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":0.7681000232696533,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.04780000075697899,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.0364999994635582,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/differential-privacy","display_name":"Differential privacy","score":0.7767999768257141},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.6083999872207642},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.59579998254776},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.5547999739646912},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5415999889373779},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.5231000185012817},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.44600000977516174},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4381999969482422},{"id":"https://openalex.org/keywords/information-sensitivity","display_name":"Information sensitivity","score":0.3587999939918518}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8075000047683716},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.7767999768257141},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.6083999872207642},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.59579998254776},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.5547999739646912},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5415999889373779},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.5231000185012817},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4381999969482422},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36469998955726624},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C3017597292","wikidata":"https://www.wikidata.org/wiki/Q25052250","display_name":"Privacy protection","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.3199999928474426},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31189998984336853},{"id":"https://openalex.org/C91262260","wikidata":"https://www.wikidata.org/wiki/Q528074","display_name":"End user","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.2655999958515167},{"id":"https://openalex.org/C69360830","wikidata":"https://www.wikidata.org/wiki/Q1172237","display_name":"Data Protection Act 1998","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C169093310","wikidata":"https://www.wikidata.org/wiki/Q3702971","display_name":"Personally identifiable information","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.25060001015663147}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1613/jair.1.21111","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.21111","pdf_url":"https://jair.org/index.php/jair/article/download/21111/27321","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2512.03238","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.03238","pdf_url":"https://arxiv.org/pdf/2512.03238","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":"pmh:oai:arXiv.org:2512.03238","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2512.03238","pdf_url":"https://arxiv.org/pdf/2512.03238","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.03238","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.03238","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1613/jair.1.21111","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.21111","pdf_url":"https://jair.org/index.php/jair/article/download/21111/27321","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417026720.pdf","grobid_xml":"https://content.openalex.org/works/W4417026720.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"High":[0],"quality":[1],"data":[2,29,38,47,93,117,129,169,177,195,214,287,297,329],"is":[3,30,49,99,136,149],"of":[4,12,27,52,54,65,100,115,159,175,200,219,241,249,295,311],"vital":[5,101],"importance":[6],"for":[7,14,59,141,153,260],"unlocking":[8,91],"the":[9,112,128,172,190,198,217,238,247,258,274,293],"full":[10,239],"potential":[11],"AI":[13,70],"end":[15,86,108],"users.":[16],"Villalobos":[17],"et":[18],"al.":[19],"stated":[20],"in":[21,95,277,308,318,326],"2024":[22],"that":[23,81,85,170,187,202,222,280,304],"finding":[24],"new":[25],"sources":[26],"such":[28],"getting":[31],"harder":[32],"as":[33],"most":[34],"publicly-available":[35],"human":[36],"generated":[37],"will":[39,72,88,306],"soon":[40],"have":[41,203,224],"been":[42,205],"used.":[43,132],"Additionally,":[44,211],"publicly":[45],"available":[46],"often":[48],"not":[50],"representative":[51],"users":[53,87,109],"a":[55,61,137,150,278],"particular":[56],"system":[57,105,279],"\u2014":[58],"example,":[60],"research":[62,317],"speech":[63],"dataset":[64],"contractors":[66],"interacting":[67],"with":[68,119],"an":[69],"assistant":[71],"likely":[73],"be":[74,125,131],"more":[75],"homogeneous,":[76],"well":[77,138],"articulated":[78],"and":[79,107,144,148,257,267,289,298,322],"self-censored":[80],"real":[82,96],"world":[83],"commands":[84],"issue.":[89],"Therefore":[90],"high-quality":[92],"grounded":[94],"user":[97,116,155],"interactions":[98],"interest":[102],"to":[103,167,185,189,208,291],"both":[104],"creators":[106],"themselves.":[110],"However,":[111],"direct":[113],"use":[114,218,294],"comes":[118],"significant":[120],"privacy":[121,183,209,250,300],"risks,":[122],"which":[123],"must":[124],"addressed":[126],"before":[127],"can":[130,196,215,255],"Differential":[133],"Privacy":[134],"(DP)":[135],"established":[139],"framework":[140],"reasoning":[142],"about":[143],"limiting":[145],"information":[146],"leakage,":[147],"gold":[151],"standard":[152],"protecting":[154],"privacy.":[156],"The":[157],"focus":[158],"this":[160,234],"work,":[161],"Differentially":[162],"Private":[163],"Synthetic":[164],"data,":[165,246,284,314],"refers":[166],"synthetic":[168,194,213,245,283,296,313,328],"preserves":[171],"overall":[173],"trends":[174],"source":[176,191],"(often":[178],"user-generated),":[179],"while":[180],"providing":[181],"strong":[182],"guarantees":[184],"individuals":[186],"contributed":[188],"dataset.":[192],"DP":[193,212,244,282,312,327],"unlock":[197],"value":[199],"datasets":[201,221],"previously":[204,223],"inaccessible":[206],"due":[207],"concerns.":[210],"replace":[216],"sensitive":[220,286],"only":[225],"had":[226],"rudimentary":[227],"protections":[228,251],"like":[229],"ad-hoc":[230],"rule-based":[231],"anonymization.":[232],"In":[233],"survey":[235],"we":[236],"explore":[237],"suite":[240],"techniques":[242],"surrounding":[243],"types":[248],"different":[252],"generation":[253],"approaches":[254],"offer,":[256],"state-of-the-art":[259],"various":[261],"modalities":[262],"including":[263],"image,":[264],"tabular,":[265],"text":[266],"federated":[268],"(decentralized)":[269],"data.":[270],"We":[271,302],"outline":[272],"all":[273],"components":[275],"needed":[276],"generates":[281],"from":[285],"handling":[288],"preparation,":[290],"tracking":[292],"empirical":[299],"testing.":[301],"hope":[303],"work":[305],"result":[307],"increased":[309],"adoption":[310],"spur":[315],"additional":[316],"still":[319],"underexplored":[320],"domains,":[321],"additionally":[323],"increase":[324],"trust":[325],"approaches.":[330]},"counts_by_year":[],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-12-05T00:00:00"}