{"id":"https://openalex.org/W7160241625","doi":"https://doi.org/10.48550/arxiv.2605.01129","title":"Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set","display_name":"Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7160241625","doi":"https://doi.org/10.48550/arxiv.2605.01129"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.01129","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01129","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":null,"license_id":null,"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.2605.01129","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135411995","display_name":"Jie Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135317086","display_name":"Nima Naderloui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naderloui, Nima","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101564806","display_name":"Da Zhong","orcid":"https://orcid.org/0000-0002-2788-5895"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Da","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135405219","display_name":"Yuan Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135292321","display_name":"Wendy Hui Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wendy Hui","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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.6539000272750854,"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":0.6539000272750854,"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":0.1340000033378601,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0414000004529953,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7193999886512756},{"id":"https://openalex.org/keywords/differential-privacy","display_name":"Differential privacy","score":0.7020000219345093},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.5533999800682068},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5457000136375427},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.5131000280380249},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44359999895095825},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3506999909877777},{"id":"https://openalex.org/keywords/information-sensitivity","display_name":"Information sensitivity","score":0.3190999925136566},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.3100000023841858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7303000092506409},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7193999886512756},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.7020000219345093},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5533999800682068},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5457000136375427},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.5131000280380249},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44359999895095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42910000681877136},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4004000127315521},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37720000743865967},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C2779201187","wikidata":"https://www.wikidata.org/wiki/Q2775060","display_name":"Information leakage","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3068000078201294},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C3017597292","wikidata":"https://www.wikidata.org/wiki/Q25052250","display_name":"Privacy protection","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C509729295","wikidata":"https://www.wikidata.org/wiki/Q7246032","display_name":"Privacy software","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C3746660","wikidata":"https://www.wikidata.org/wiki/Q1068763","display_name":"Rule of inference","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C69360830","wikidata":"https://www.wikidata.org/wiki/Q1172237","display_name":"Data Protection Act 1998","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.01129","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01129","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.01129","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01129","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":null,"license_id":null,"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","score":0.7724344730377197,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Machine":[0],"unlearning":[1,62,74,91,106,115],"(MU)":[2],"has":[3],"emerged":[4],"as":[5],"a":[6,80,138,177],"key":[7],"mechanism":[8],"for":[9],"ensuring":[10],"data":[11,33,43],"privacy":[12,37,59,119,168,181],"and":[13,89,98,108,145,162,183],"regulatory":[14],"compliance":[15],"by":[16,171],"enabling":[17],"models":[18],"to":[19,39,63,92,121,129,165],"forget":[20],"specific":[21],"training":[22],"samples.":[23],"However,":[24],"recent":[25],"studies":[26],"have":[27],"shown":[28],"that":[29,44,84],"the":[30,40,47,56,64,71,95,122,150,167,187,191],"removal":[31],"of":[32,58,141],"can":[34,116],"inadvertently":[35],"introduce":[36,69,117],"leakages":[38],"retain":[41,123],"set,i.e.,":[42],"remain":[45],"in":[46,61],"model":[48,86,142,184],"after":[49,90],"unlearning.":[50],"In":[51],"this":[52],"paper,":[53],"we":[54,152],"extend":[55],"scope":[57],"analysis":[60],"often-overlooked":[65],"retained":[66],"data.":[67],"We":[68],"TC-UMIA,":[70],"first":[72],"tri-class":[73],"membership":[75,130],"inference":[76,82,131],"attack.":[77],"TC-UMIA":[78,134],"is":[79,135],"population-level":[81],"framework":[83],"leverages":[85],"predictions":[87],"before":[88],"distinguish":[93],"among":[94],"forget,":[96],"retain,":[97],"unseen":[99],"set.":[100],"Extensive":[101],"experiments":[102],"on":[103],"five":[104],"state-of-the-art":[105],"algorithms":[107],"six":[109],"real-world":[110],"datasets":[111],"demonstrate":[112],"that:":[113],"(i)":[114],"additional":[118],"risks":[120,169],"set,":[124],"making":[125],"it":[126],"more":[127],"susceptible":[128],"attacks;":[132],"(ii)":[133],"effective":[136],"across":[137],"wide":[139],"range":[140],"architectures,":[143],"datasets,":[144],"MU":[146],"approaches.":[147],"Beyond":[148],"launching":[149],"attack,":[151],"rigorously":[153],"evaluate":[154],"three":[155],"defense":[156],"mechanisms,":[157],"namely":[158],"label-only":[159],"outputs,":[160],"dropout,":[161],"differential":[163],"privacy,":[164],"mitigate":[166],"posed":[170],"TC-":[172],"UMIA.":[173],"Our":[174],"results":[175],"reveal":[176],"fundamental":[178],"trade-off":[179],"between":[180],"protection":[182],"accuracy,":[185],"with":[186],"dropout":[188],"approach":[189],"offering":[190],"most":[192],"favorable":[193],"balance.":[194]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-06T00:00:00"}