{"id":"https://openalex.org/W7162468533","doi":"https://doi.org/10.48550/arxiv.2605.25819","title":"On Reliability of Efficient Membership Inference Vulnerability Evaluation","display_name":"On Reliability of Efficient Membership Inference Vulnerability Evaluation","publication_year":2026,"publication_date":"2026-05-25","ids":{"openalex":"https://openalex.org/W7162468533","doi":"https://doi.org/10.48550/arxiv.2605.25819"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.25819","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25819","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,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.25819","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016678094","display_name":"Joonas J\u00e4lk\u00f6","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J\u00e4lk\u00f6, Joonas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042258127","display_name":"Gauri Pradhan","orcid":"https://orcid.org/0009-0003-7267-6309"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pradhan, Gauri","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008120025","display_name":"Ossi R\u00e4is\u00e4","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R\u00e4is\u00e4, Ossi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137043807","display_name":"Antti Honkela","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Honkela, Antti","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5231999754905701,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5231999754905701,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.35269999504089355,"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/T10734","display_name":"Information and Cyber Security","score":0.014999999664723873,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5899999737739563},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.43549999594688416},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.39890000224113464},{"id":"https://openalex.org/keywords/sampling-bias","display_name":"Sampling bias","score":0.39320001006126404},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.3808000087738037},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.37869998812675476},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.37310001254081726},{"id":"https://openalex.org/keywords/false-positive-rate","display_name":"False positive rate","score":0.37209999561309814},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.36320000886917114}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5899999737739563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5309000015258789},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5189999938011169},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49129998683929443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4683000147342682},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.43549999594688416},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C75917345","wikidata":"https://www.wikidata.org/wiki/Q2725298","display_name":"Sampling bias","level":3,"score":0.39320001006126404},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C95922358","wikidata":"https://www.wikidata.org/wiki/Q5432725","display_name":"False positive rate","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.36320000886917114},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.32199999690055847},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3000999987125397},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.295199990272522},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C3020402766","wikidata":"https://www.wikidata.org/wiki/Q104376712","display_name":"Prior information","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.26600000262260437},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25699999928474426},{"id":"https://openalex.org/C3020318244","wikidata":"https://www.wikidata.org/wiki/Q4812187","display_name":"Large sample","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C167063184","wikidata":"https://www.wikidata.org/wiki/Q1400839","display_name":"Vulnerability assessment","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C112789634","wikidata":"https://www.wikidata.org/wiki/Q18207010","display_name":"False positives and false negatives","level":3,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.25819","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25819","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,"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:10.48550/arxiv.2605.25819","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.25819","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,"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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7411415576934814}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Membership":[0],"inference":[1],"attacks":[2],"(MIAs)":[3],"are":[4,77,102],"popular":[5],"methods":[6],"for":[7,69,163],"empirically":[8],"assessing":[9],"the":[10,16,25,57,66,99,128,144,153,178,191,211],"leakage":[11],"of":[12,43,75,82],"sensitive":[13],"information":[14],"in":[15,56,61,80,117,143,190,210],"training":[17,58],"data":[18],"through":[19,33],"models":[20],"or":[21],"statistics":[22],"learned":[23],"from":[24],"data.":[26,59],"The":[27],"MIA":[28,83,100,120,132],"vulnerability":[29],"is":[30,149],"often":[31,103],"evaluated":[32],"false":[34],"positive":[35,40,208],"rate":[36,41],"(FPR)":[37],"and":[38,108],"true":[39],"(TPR)":[42],"a":[44,52,73,161,172,186,207],"binary":[45],"classifier":[46],"that":[47,126],"tries":[48],"to":[49,63,85,90,140,175,206],"predict":[50],"whether":[51],"particular":[53],"sample":[54],"was":[55],"However,":[60],"order":[62],"reliably":[64],"estimate":[65],"TPR":[67,129],"especially":[68],"low":[70,146],"FPR":[71,147,179],"values,":[72],"lot":[74],"observations":[76],"needed,":[78],"which":[79],"case":[81],"translates":[84],"many":[86],"target":[87],"models,":[88],"leading":[89,205],"large":[91],"computational":[92],"cost.":[93],"To":[94,167],"avoid":[95],"excessive":[96],"compute":[97],"requirements,":[98],"scores":[101,133],"averaged":[104],"over":[105],"multiple":[106,109,136],"individuals":[107],"targeted":[110],"models.":[111],"We":[112],"demonstrate":[113],"two":[114],"key":[115],"weaknesses":[116],"this":[118],"efficient":[119,194],"evaluation":[121],"pipeline.":[122],"First,":[123],"we":[124,170,184],"show":[125],"evaluating":[127],"based":[130],"on":[131],"concatenated":[134],"across":[135,152,180],"individuals,":[137],"commonly":[138,192],"used":[139,193],"study":[141],"vulnerabilities":[142],"very":[145],"regime,":[148],"not":[150],"calibrated":[151],"per-sample":[154,212],"FPRs.":[155],"This":[156],"makes":[157],"it":[158],"unreliable":[159],"as":[160],"tool":[162],"auditing":[164],"differential":[165],"privacy.":[166],"solve":[168],"this,":[169],"propose":[171],"post-processing":[173],"method":[174],"effectively":[176],"calibrate":[177],"different":[181],"samples.":[182],"Second,":[183],"identify":[185],"finite":[187],"population":[188],"bias":[189,209],"likelihood-ratio":[195],"attack":[196],"(LiRA)":[197],"implementation":[198],"proposed":[199],"by":[200],"Carlini":[201],"et":[202],"al.":[203],"2022,":[204],"vulnerability.":[213]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-27T00:00:00"}