{"id":"https://openalex.org/W7162777769","doi":"https://doi.org/10.48550/arxiv.2605.29454","title":"A Full-Pipeline Framework for Evaluating Membership Inference Attacks in Machine Learning","display_name":"A Full-Pipeline Framework for Evaluating Membership Inference Attacks in Machine Learning","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162777769","doi":"https://doi.org/10.48550/arxiv.2605.29454"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.29454","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29454","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":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.2605.29454","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137389875","display_name":"Ding Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110416829","display_name":"Xinwen Cheng","orcid":"https://orcid.org/0000-0001-6080-0614"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Xinwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137362028","display_name":"Xuyang Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Xuyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137321566","display_name":"Xinping Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xinping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137392221","display_name":"Xiaolin Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Xiaolin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137357093","display_name":"Chen Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Chen","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":0.5849000215530396,"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":0.5849000215530396,"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":0.2924000024795532,"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":0.0210999995470047,"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/audit","display_name":"Audit","score":0.7032999992370605},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.6585999727249146},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6011999845504761},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5454999804496765},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.44290000200271606},{"id":"https://openalex.org/keywords/adversarial-machine-learning","display_name":"Adversarial machine learning","score":0.4090999960899353},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.3481999933719635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7267000079154968},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.7032999992370605},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6836000084877014},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.6585999727249146},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6011999845504761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5867000222206116},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5454999804496765},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.44290000200271606},{"id":"https://openalex.org/C2778403875","wikidata":"https://www.wikidata.org/wiki/Q20312394","display_name":"Adversarial machine learning","level":3,"score":0.4090999960899353},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.33070001006126404},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2955000102519989},{"id":"https://openalex.org/C2780264999","wikidata":"https://www.wikidata.org/wiki/Q7445032","display_name":"Security domain","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C140547941","wikidata":"https://www.wikidata.org/wiki/Q7797194","display_name":"Threat model","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.29454","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29454","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":"doi:10.48550/arxiv.2605.29454","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29454","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.544482946395874,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"Membership":[1],"Inference":[2],"Attacks":[3],"(MIAs)":[4],"are":[5,154],"the":[6,24,58,84,189,199],"prevailing":[7],"method":[8],"for":[9,30,118,132,145],"identifying":[10],"training":[11,114],"data,":[12,90],"their":[13],"application":[14],"has":[15],"expanded":[16],"into":[17,176,212],"privacy":[18,81,226],"auditing":[19,219],"and":[20,68,93,172,203,215],"machine":[21,86],"unlearning.":[22],"Nevertheless,":[23],"field":[25],"lacks":[26],"a":[27,40,74,110,217],"systematic":[28],"framework":[29,77,104],"evaluating":[31],"how":[32],"different":[33],"contexts":[34],"affect":[35],"MIA":[36,193],"efficacy.":[37],"Without":[38],"such":[39],"characterization,":[41],"practitioners":[42,222],"risk":[43],"deploying":[44],"algorithms":[45],"that":[46,78,159,188],"perform":[47],"well":[48],"on":[49],"benchmarks":[50],"but":[51],"become":[52],"statistically":[53],"irrelevant":[54],"when":[55],"faced":[56],"with":[57],"nuances":[59],"of":[60,113,191],"specific,":[61],"real-world":[62,123],"datasets.":[63],"To":[64,116],"bridge":[65],"this":[66],"gap":[67],"provide":[69,216],"actionable":[70,213],"insights,":[71],"we":[72,125,166,208],"introduce":[73],"comprehensive":[75],"evaluation":[76,205],"systematically":[79],"characterizes":[80],"risks":[82],"across":[83,109],"entire":[85],"learning":[87],"pipeline,":[88],"spanning":[89],"architectures,":[91],"algorithms,":[92],"post-training":[94],"modules.":[95],"Designed":[96],"to":[97,179,198,223],"inherently":[98],"capture":[99],"diverse":[100],"operational":[101],"contexts,":[102],"our":[103],"rigorously":[105],"evaluates":[106],"state-of-the-art":[107],"MIAs":[108,161],"broad":[111],"spectrum":[112],"configurations.":[115],"account":[117],"varying":[119],"misclassification":[120],"costs":[121],"in":[122],"deployments,":[124],"employ":[126],"three":[127],"complementary":[128],"metrics:":[129],"Balanced":[130],"Accuracy":[131],"symmetric":[133],"costs,":[134],"alongside":[135],"TPR":[136],"at":[137,142],"low":[138,143],"FPR":[139],"(or":[140],"TNR":[141],"FNR)":[144],"asymmetric":[146],"scenarios":[147],"where":[148],"false":[149],"alarms":[150],"or":[151],"missed":[152],"detections":[153],"strictly":[155],"penalized.":[156],"Furthermore,":[157],"recognizing":[158],"existing":[160],"assume":[162],"divergent":[163],"adversary":[164],"capabilities,":[165],"formalize":[167],"two":[168],"standardized":[169],"threat":[170,201],"models":[171,202],"adapt":[173],"these":[174,210],"attacks":[175],"corresponding":[177],"variants":[178],"ensure":[180],"an":[181],"equitable":[182],"benchmark.":[183],"Extensive":[184],"empirical":[185],"evaluations":[186],"demonstrate":[187],"efficacy":[190],"specific":[192],"methodologies":[194],"is":[195],"highly":[196],"sensitive":[197],"assumed":[200],"chosen":[204],"metrics.":[206],"Ultimately,":[207],"distill":[209],"findings":[211],"guidelines":[214],"ready-to-use":[218],"toolkit,":[220],"empowering":[221],"conduct":[224],"better":[225],"assessments.":[227]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-30T00:00:00"}