{"id":"https://openalex.org/W7220455249","doi":"https://doi.org/10.48550/arxiv.2610.02414","title":"Unifying Privacy Accounting: Information Equivalence and Information Loss","display_name":"Unifying Privacy Accounting: Information Equivalence and Information Loss","publication_year":2026,"publication_date":"2026-10-01","ids":{"openalex":"https://openalex.org/W7220455249","doi":"https://doi.org/10.48550/arxiv.2610.02414"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.02414","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.02414","pdf_url":"https://arxiv.org/pdf/2610.02414","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.02414","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004846721","display_name":"\u82cf\u6b65\u65b0","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Su, Buxin","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157654031","display_name":"Qiaoshi Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang, Qiaoshi","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157634937","display_name":"Yiding Su","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Su, Yiding","raw_affiliation_strings":["University of Warwick ;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Warwick ;","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5157593090","display_name":"Chendi Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Chendi","raw_affiliation_strings":["Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"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":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/T11614","display_name":"Cloud Data Security Solutions","score":0.0,"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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/differential-privacy","display_name":"differential privacy","score":0.9350000023841858},{"id":"https://openalex.org/keywords/privacy-accounting","display_name":"privacy accounting","score":0.9340000152587891},{"id":"https://openalex.org/keywords/renyi-differential-privacy","display_name":"R\u00e9nyi differential privacy","score":0.9760000109672546},{"id":"https://openalex.org/keywords/information-equivalence","display_name":"information equivalence","score":0.7239999771118164},{"id":"https://openalex.org/keywords/information-loss","display_name":"information loss","score":0.8119999766349792},{"id":"https://openalex.org/keywords/noise-mechanisms","display_name":"noise mechanisms","score":0.5429999828338623},{"id":"https://openalex.org/keywords/gaussian-mixture-noise","display_name":"Gaussian mixture noise","score":0.703000009059906},{"id":"https://openalex.org/keywords/laplace-mechanism","display_name":"Laplace mechanism","score":0.7009999752044678},{"id":"https://openalex.org/keywords/dp-sgd","display_name":"DP-SGD","score":0.7929999828338623},{"id":"https://openalex.org/keywords/privacy-utility-trade-off","display_name":"privacy-utility trade-off","score":0.7820000052452087}],"concepts":[{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.89410001039505},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.5813000202178955},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.49709999561309814},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.47620001435279846},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4318000078201294},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.423799991607666},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.4090000092983246},{"id":"https://openalex.org/C100906024","wikidata":"https://www.wikidata.org/wiki/Q205692","display_name":"Poisson distribution","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.34529998898506165},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.28119999170303345},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C2777044963","wikidata":"https://www.wikidata.org/wiki/Q5384707","display_name":"Equivalence class (music)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.2685000002384186},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.02414","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.02414","pdf_url":"https://arxiv.org/pdf/2610.02414","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"doi:10.48550/arxiv.2610.02414","doi":"https://doi.org/10.48550/arxiv.2610.02414","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.02414","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.02414","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.02414","pdf_url":"https://arxiv.org/pdf/2610.02414","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220455249.pdf","grobid_xml":"https://content.openalex.org/works/W7220455249.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3049256126","https://openalex.org/W7221785798","https://openalex.org/W3167530662","https://openalex.org/W2130964760","https://openalex.org/W2294380383","https://openalex.org/W3017088008","https://openalex.org/W4415593616","https://openalex.org/W3169733032","https://openalex.org/W2986886197","https://openalex.org/W4389775201"],"abstract_inverted_index":{"Differential":[0],"privacy":[1,14,26,49,68,109,121,186,228],"(DP)":[2],"admits":[3],"several":[4],"notions,":[5],"but":[6,152],"the":[7,46,53,60,104,107,113,129,133,170,183,189,198,215,249],"choice":[8],"among":[9,45,90],"them":[10],"may":[11],"affect":[12],"both":[13,245],"analysis":[15],"and":[16,59,98,137,160],"utility.":[17],"In":[18,101],"this":[19,72,86,165],"paper,":[20],"we":[21,41],"consider":[22],"four":[23],"mainstream":[24],"curve-based":[25],"notions":[27,92],"within":[28],"a":[29,34,117,241],"unified":[30],"information-theoretic":[31,177],"framework.":[32],"For":[33,219],"fixed":[35],"ordered":[36],"pair":[37,54],"of":[38,51,55,106,172],"output":[39],"distributions,":[40],"establish":[42],"information":[43,130],"equivalence":[44,73],"two":[47],"directional":[48,108],"profiles":[50,110],"$(\\varepsilon,\u03b4)$-DP,":[52],"hypothesis-testing":[56],"trade-off":[57],"functions,":[58],"extended":[61],"privacy-loss":[62],"distribution.":[63],"The":[64],"exact":[65,134],"R\u00e9nyi":[66],"differential":[67,120],"(RDP)":[69],"curve":[70,115,136,192],"joins":[71],"class":[74],"whenever":[75],"it":[76],"is":[77,147],"finite":[78],"at":[79],"some":[80],"order":[81],"greater":[82],"than":[83,194],"one.":[84],"Under":[85],"mild":[87],"condition,":[88],"choosing":[89],"these":[91],"changes":[93],"only":[94],"their":[95],"semantic":[96],"interpretation":[97],"computational":[99],"requirements.":[100],"contrast,":[102],"taking":[103],"maximum":[105],"or":[111],"compressing":[112],"RDP":[114,135,191],"into":[116],"single":[118],"zero-concentrated":[119],"(zCDP)":[122],"parameter":[123],"can":[124],"lose":[125],"information.":[126],"We":[127],"quantify":[128],"loss":[131],"between":[132],"its":[138],"zCDP":[139,196],"bound":[140],"for":[141,149,155,206],"standard":[142],"noise":[143,151,200,208],"mechanisms.":[144,163,175],"This":[145],"gap":[146,166],"zero":[148],"Gaussian":[150,162],"generally":[153],"positive":[154],"Gaussian-mixture,":[156],"Laplace,":[157],"discrete":[158],"Gaussian,":[159],"Poisson-subsampled":[161],"Moreover,":[164],"grows":[167],"linearly":[168],"with":[169],"number":[171],"independently":[173],"composed":[174],"Our":[176],"perspective":[178],"has":[179],"practical":[180],"consequences.":[181],"At":[182],"same":[184,250],"certified":[185],"level,":[187],"retaining":[188],"full":[190],"rather":[193],"using":[195],"reduces":[197],"required":[199],"variance":[201],"by":[202,233],"up":[203,234],"to":[204,214,235,240,248],"$45\\%$":[205],"Gaussian-mixture":[207],"in":[209,212],"workloads":[210],"comparable":[211],"size":[213],"American":[216],"Community":[217],"Survey.":[218],"DP-SGD":[220],"on":[221],"Fashion-MNIST":[222],"under":[223],"Poisson":[224],"subsampling,":[225],"an":[226],"RDP-based":[227],"accountant":[229,243],"improves":[230],"test":[231],"accuracy":[232],"$8.73$":[236],"percentage":[237],"points":[238],"compared":[239],"zCDP-based":[242],"when":[244],"are":[246],"calibrated":[247],"$(\\varepsilon,\u03b4)$":[251],"guarantee.":[252]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-06T00:00:00"}