{"id":"https://openalex.org/W7166180438","doi":"https://doi.org/10.60882/cispa.32801004","title":"From Differential Privacy to Bounds on Membership Inference: Less can be More","display_name":"From Differential Privacy to Bounds on Membership Inference: Less can be More","publication_year":2024,"publication_date":"2024-03-24","ids":{"openalex":"https://openalex.org/W7166180438","doi":"https://doi.org/10.60882/cispa.32801004"},"language":"en","primary_location":{"id":"doi:10.60882/cispa.32801004","doi":"https://doi.org/10.60882/cispa.32801004","is_oa":true,"landing_page_url":"https://doi.org/10.60882/cispa.32801004","pdf_url":null,"source":{"id":"https://openalex.org/S4393919742","display_name":"Transactions on machine learning research","issn_l":"2835-8856","issn":["2835-8856"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj","jufo-1","norway-1","vabb-shw"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.60882/cispa.32801004","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010910495","display_name":"Anvith Thudi","orcid":"https://orcid.org/0009-0005-9062-7863","observed_orcids":["https://orcid.org/0009-0005-9062-7863"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anvith Thudi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139445612","display_name":"Ilia Shumailov","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ilia Shumailov","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039583147","display_name":"Franziska Boenisch","orcid":"https://orcid.org/0000-0002-2111-2234","observed_orcids":["https://orcid.org/0000-0002-2111-2234"]},"institutions":[{"id":"https://openalex.org/I4210128801","display_name":"Helmholtz Center for Information Security","ror":"https://ror.org/02njgxr09","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210128801"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Franziska Boenisch","raw_affiliation_strings":["Helmholtz Center for Information Security"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Helmholtz Center for Information Security","institution_ids":["https://openalex.org/I4210128801"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018809423","display_name":"Nicolas Papernot","orcid":"https://orcid.org/0000-0001-5078-7233","observed_orcids":["https://orcid.org/0000-0001-5078-7233"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nicolas Papernot","raw_affiliation_strings":[],"raw_orcid":null,"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":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30689062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/differential-privacy","display_name":"differential privacy","score":0.968999981880188},{"id":"https://openalex.org/keywords/membership-inference-attacks","display_name":"membership inference attacks","score":0.9879999756813049},{"id":"https://openalex.org/keywords/training-set-size","display_name":"training data size","score":0.7760000228881836},{"id":"https://openalex.org/keywords/privacy-utility-trade-off","display_name":"privacy-utility trade-off","score":0.859000027179718},{"id":"https://openalex.org/keywords/training-sample-selection","display_name":"training data selection","score":0.38100001215934753},{"id":"https://openalex.org/keywords/privacy-preserving-machine-learning","display_name":"privacy-preserving machine learning","score":0.5789999961853027},{"id":"https://openalex.org/keywords/neural-network-privacy","display_name":"neural network privacy","score":0.37400001287460327}],"concepts":[{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.805400013923645},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6949999928474426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5328999757766724},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.5127999782562256},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4569999873638153},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41990000009536743},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C3017597292","wikidata":"https://www.wikidata.org/wiki/Q25052250","display_name":"Privacy protection","level":2,"score":0.3869999945163727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3720000088214874},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.33390000462532043},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C2992317946","wikidata":"https://www.wikidata.org/wiki/Q712144","display_name":"De facto","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32179999351501465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31679999828338623},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3147999942302704},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C134121241","wikidata":"https://www.wikidata.org/wiki/Q899301","display_name":"Yield (engineering)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.2572000026702881}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.60882/cispa.32801004","doi":"https://doi.org/10.60882/cispa.32801004","is_oa":true,"landing_page_url":"https://doi.org/10.60882/cispa.32801004","pdf_url":null,"source":{"id":"https://openalex.org/S4393919742","display_name":"Transactions on machine learning research","issn_l":"2835-8856","issn":["2835-8856"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj","jufo-1","norway-1","vabb-shw"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},{"id":"doi:10.60882/cispa.32801004.v1","doi":"https://doi.org/10.60882/cispa.32801004.v1","is_oa":true,"landing_page_url":"https://doi.org/10.60882/cispa.32801004.v1","pdf_url":null,"source":{"id":"https://openalex.org/S4393919742","display_name":"Transactions on machine learning research","issn_l":"2835-8856","issn":["2835-8856"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj","jufo-1","norway-1","vabb-shw"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"doi:10.60882/cispa.32801004","doi":"https://doi.org/10.60882/cispa.32801004","is_oa":true,"landing_page_url":"https://doi.org/10.60882/cispa.32801004","pdf_url":null,"source":{"id":"https://openalex.org/S4393919742","display_name":"Transactions on machine learning research","issn_l":"2835-8856","issn":["2835-8856"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj","jufo-1","norway-1","vabb-shw"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3094387590","https://openalex.org/W4226540977","https://openalex.org/W3206966921","https://openalex.org/W4309129611","https://openalex.org/W6981139341","https://openalex.org/W4388745351","https://openalex.org/W4224022788","https://openalex.org/W4386215192","https://openalex.org/W2998452322","https://openalex.org/W3181858657"],"abstract_inverted_index":{"Differential":[0],"Privacy":[1],"(DP)":[2],"is":[3,156],"the":[4,11,58,77,113,126,131,139,145,150,178],"de":[5],"facto":[6],"standard":[7],"for":[8],"reasoning":[9],"about":[10,155],"privacy":[12,151],"of":[13,61,79,96,115],"a":[14,29,93,97,135],"training":[15,39,117,132,161],"algorithm.":[16],"Yet,":[17],"learning":[18],"with":[19],"DP":[20,98,146,179],"often":[21],"yields":[22],"poor":[23],"performance":[24],"unless":[25],"one":[26],"trains":[27],"on":[28,40,76,138,162,185],"large":[30],"dataset.":[31],"In":[32],"this":[33,69,184],"paper,":[34],"we":[35,47,56,71,121,153],"instead":[36],"outline":[37],"how":[38,116],"less":[41,163],"data":[42,118,164],"can":[43,122,165],"be":[44],"beneficial":[45],"when":[46,129,141,149],"are":[48],"only":[49],"interested":[50],"in":[51],"defending":[52,62,157],"against":[53,63,103,158],"specific":[54],"attacks;":[55],"take":[57],"canonical":[59],"example":[60],"membership":[64,81,104,159,172],"inference.":[65],"To":[66],"arrive":[67],"at":[68],"result,":[70],"first":[72],"derive":[73],"(tight)":[74],"bounds":[75,85],"success":[78],"all":[80],"inference":[82,105,173],"attacks.":[83],"These":[84],"do":[86],"not":[87],"replace":[88],"DP,":[89],"rather":[90],"they":[91],"introduce":[92],"complementary":[94],"interpretation":[95],"algorithm\u2019s":[99],"ability":[100],"to":[101,143],"defend":[102],"specifically.":[106],"Because":[107],"our":[108],"bound":[109,140],"more":[110,167],"tightly":[111],"captures":[112],"effect":[114,137],"was":[119],"selected,":[120],"show":[123],"that":[124],"decreasing":[125],"sampling":[127],"rate":[128],"constructing":[130],"dataset":[133],"has":[134],"disparate":[136],"compared":[142],"strengthening":[144,177],"guarantee.":[147,180],"Thus,":[148],"protection":[152],"care":[154],"inference,":[160],"yield":[166],"advantageous":[168],"trade-offs":[169],"between":[170],"preventing":[171],"and":[174,188],"utility":[175],"than":[176],"We":[181],"empirically":[182],"illustrate":[183],"MNIST,":[186],"CIFAR10":[187],"SVHN-extended.":[189]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-06-27T00:00:00"}