{"id":"https://openalex.org/W7134831152","doi":"https://doi.org/10.48550/arxiv.2603.07567","title":"Revisiting the LiRA Membership Inference Attack Under Realistic Assumptions","display_name":"Revisiting the LiRA Membership Inference Attack Under Realistic Assumptions","publication_year":2026,"publication_date":"2026-03-08","ids":{"openalex":"https://openalex.org/W7134831152","doi":"https://doi.org/10.48550/arxiv.2603.07567"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.07567","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016893172","display_name":"Najeeb Jebreel","orcid":"https://orcid.org/0000-0002-4911-3802"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jebreel, Najeeb","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128641737","display_name":"Mona Khalil","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khalil, Mona","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128649646","display_name":"David S\u00e1nchez","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S\u00e1nchez, David","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5109255913","display_name":"Josep Domingo-Ferrer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Domingo-Ferrer, Josep","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":0.8664000034332275,"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":0.8664000034332275,"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":0.0471000000834465,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.018699999898672104,"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/overconfidence-effect","display_name":"Overconfidence effect","score":0.7368999719619751},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5342000126838684},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.44999998807907104},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4433000087738037},{"id":"https://openalex.org/keywords/shadow","display_name":"Shadow (psychology)","score":0.3887999951839447},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.32420000433921814},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.30649998784065247},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.29580000042915344}],"concepts":[{"id":"https://openalex.org/C51110983","wikidata":"https://www.wikidata.org/wiki/Q16503490","display_name":"Overconfidence effect","level":2,"score":0.7368999719619751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.550599992275238},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5342000126838684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48809999227523804},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.460099995136261},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.44999998807907104},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4433000087738037},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.4269999861717224},{"id":"https://openalex.org/C117797892","wikidata":"https://www.wikidata.org/wiki/Q286363","display_name":"Shadow (psychology)","level":2,"score":0.3887999951839447},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38760000467300415},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.32420000433921814},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.29580000042915344},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C9893847","wikidata":"https://www.wikidata.org/wiki/Q1425625","display_name":"Reproducibility","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2736999988555908},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C2779267917","wikidata":"https://www.wikidata.org/wiki/Q170028","display_name":"Deception","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C2777163752","wikidata":"https://www.wikidata.org/wiki/Q6557574","display_name":"Lira","level":3,"score":0.2535000145435333},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.07567","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},{"id":"doi:10.48550/arxiv.2603.07567","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.07567","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":"pmh:doi:10.48550/arxiv.2603.07567","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"sustainable_development_goals":[],"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],"have":[4,41],"become":[5],"the":[6,19,27,30,44],"standard":[7],"tool":[8],"for":[9],"evaluating":[10],"privacy":[11,215],"leakage":[12],"in":[13,93],"machine":[14],"learning":[15,85],"(ML).":[16],"Among":[17],"them,":[18],"Likelihood-Ratio":[20],"Attack":[21],"(LiRA)":[22],"is":[23,232],"widely":[24],"regarded":[25],"as":[26,92],"state":[28],"of":[29,46],"art":[31],"when":[32,87],"sufficient":[33],"shadow":[34,101],"models":[35,50,79,102],"are":[36,191,203],"available.":[37],"However,":[38],"prior":[39],"evaluations":[40],"often":[42,164],"overstated":[43],"effectiveness":[45,151],"LiRA":[47,71],"by":[48],"attacking":[49],"overconfident":[51],"on":[52,58],"their":[53],"training":[54,137,223],"samples,":[55],"calibrating":[56],"thresholds":[57,99,119,158],"target":[59,107],"data,":[60],"assuming":[61],"balanced":[62],"membership":[63,122,131],"priors,":[64,161],"and/or":[65],"overlooking":[66],"attack":[67,150],"reproducibility.":[68],"We":[69,139,172],"re-evaluate":[70],"under":[72,117,168,209],"a":[73],"realistic":[74,210],"protocol":[75],"that":[76,141,175,197,213,220],"(i)":[77],"trains":[78],"using":[80,100],"anti-overfitting":[81],"(AOF)":[82],"and":[83,103,120,127,136,159,199,212,228],"transfer":[84],"(TL),":[86],"applicable,":[88],"to":[89],"reduce":[90],"overconfidence":[91],"production":[94],"models;":[95],"(ii)":[96],"calibrates":[97],"decision":[98],"data":[104],"rather":[105],"than":[106,206],"data;":[108],"(iii)":[109],"measures":[110],"positive":[111],"predictive":[112],"value":[113],"(PPV,":[114],"or":[115,170],"precision)":[116],"shadow-based":[118,157],"skewed":[121,160],"priors":[123],"(pi":[124],"<=":[125],"10%);":[126],"(iv)":[128],"quantifies":[129],"per-sample":[130],"reproducibility":[132,185,229],"across":[133,186],"different":[134],"seeds":[135],"variations.":[138],"find":[140,174],"AOF":[142,169],"significantly":[143],"weakens":[144],"LiRA,":[145,198],"while":[146,152,188],"TL":[147],"further":[148],"reduces":[149],"improving":[153],"model":[154],"accuracy.":[155],"Under":[156],"LiRA's":[162],"PPV":[163],"drops":[165],"substantially,":[166],"especially":[167],"AOF+TL.":[171],"also":[173],"thresholded":[176],"vulnerable":[177],"sets":[178],"at":[179,234],"extremely":[180],"low":[181],"FPR":[182],"show":[183],"poor":[184],"runs,":[187],"likelihood-ratio":[189],"rankings":[190],"more":[192],"stable.":[193],"These":[194],"results":[195],"suggest":[196],"likely":[200],"weaker":[201],"MIAs,":[202],"less":[204],"effective":[205],"previously":[207],"suggested":[208],"conditions,":[211],"reliable":[214],"auditing":[216],"requires":[217],"evaluation":[218],"protocols":[219],"reflect":[221],"practical":[222],"practices,":[224],"feasible":[225],"attacker":[226],"assumptions,":[227],"considerations.":[230],"Code":[231],"available":[233],"https://github.com/najeebjebreel/lira_analysis.":[235]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-11T00:00:00"}