{"id":"https://openalex.org/W4414540033","doi":"https://doi.org/10.1109/icc52391.2025.11161721","title":"Membership Inference Attack Against Bayesian Neural Network","display_name":"Membership Inference Attack Against Bayesian Neural Network","publication_year":2025,"publication_date":"2025-06-08","ids":{"openalex":"https://openalex.org/W4414540033","doi":"https://doi.org/10.1109/icc52391.2025.11161721"},"language":"en","primary_location":{"id":"doi:10.1109/icc52391.2025.11161721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11161721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on Communications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027436126","display_name":"Toshiki Shibahara","orcid":"https://orcid.org/0000-0002-2192-4355"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Toshiki Shibahara","raw_affiliation_strings":["NTT Social Informatics Laboratories,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Social Informatics Laboratories,Tokyo,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103184456","display_name":"Takayuki Miura","orcid":"https://orcid.org/0000-0001-8694-312X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takayuki Miura","raw_affiliation_strings":["NTT Social Informatics Laboratories,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Social Informatics Laboratories,Tokyo,Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068183783","display_name":"Masanobu Kii","orcid":"https://orcid.org/0000-0003-1774-4308"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masanobu Kii","raw_affiliation_strings":["NTT Social Informatics Laboratories,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Social Informatics Laboratories,Tokyo,Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042705001","display_name":"Atsunori Ichikawa","orcid":"https://orcid.org/0000-0001-8013-7071"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Atsunori Ichikawa","raw_affiliation_strings":["NTT Social Informatics Laboratories,Tokyo,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Social Informatics Laboratories,Tokyo,Japan","institution_ids":[]}]}],"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":"5640","last_page":"5645"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.965399980545044,"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":0.965399980545044,"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":0.5889999866485596},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5564000010490417},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5090000033378601},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5085999965667725},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.48989999294281006},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.45010000467300415},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.3716000020503998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7372999787330627},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5889999866485596},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5564000010490417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5439000129699707},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5090000033378601},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5085999965667725},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5044000148773193},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.48989999294281006},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47870001196861267},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.45010000467300415},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3716000020503998},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.34769999980926514},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.30889999866485596},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2930000126361847},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C37903108","wikidata":"https://www.wikidata.org/wiki/Q4874474","display_name":"Bayesian linear regression","level":4,"score":0.26600000262260437},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.2639000117778778}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icc52391.2025.11161721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc52391.2025.11161721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICC 2025 - IEEE International Conference on Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2051267297","https://openalex.org/W2535690855","https://openalex.org/W2795435272","https://openalex.org/W2964059111","https://openalex.org/W3043426275","https://openalex.org/W3096692244","https://openalex.org/W4288057780","https://openalex.org/W4308644392","https://openalex.org/W4385679781"],"related_works":[],"abstract_inverted_index":{"Membership":[0],"Inference":[1],"Attacks":[2],"(MIAs)":[3],"have":[4],"been":[5],"actively":[6],"studied":[7],"to":[8,35,38,59],"evaluate":[9,43],"the":[10,44,57,64,72,81,98,130,143],"privacy":[11,45,137,144],"risks":[12,46,145],"of":[13,47,74],"training":[14],"data.":[15],"However,":[16],"existing":[17],"MIAs":[18,31,103],"focus":[19],"on":[20,63,129],"deterministic":[21,33],"deep":[22],"neural":[23],"networks":[24],"(DNNs).":[25],"In":[26],"this":[27],"paper,":[28],"we":[29,50,84,140],"extend":[30],"against":[32],"DNNs":[34],"be":[36,147],"applicable":[37],"Bayesian":[39],"NNs":[40],"(BNNs)":[41],"and":[42,101,117],"BNNs.":[48,120],"Specifically,":[49],"propose":[51,86],"four":[52,87],"MIAs,":[53],"each":[54],"differing":[55],"in":[56],"extent":[58],"which":[60],"detailed":[61,127],"information":[62,128],"posterior":[65,131],"predictive":[66,132],"distribution":[67,133],"is":[68],"exploited.":[69],"Additionally,":[70,139],"considering":[71],"trait":[73],"BNNs":[75,94],"that":[76,124,142],"produce":[77],"different":[78],"outputs":[79],"for":[80,114],"same":[82,99],"input,":[83],"also":[85],"multiple":[88,95,152],"query":[89,93],"attacks":[90],"where":[91],"attackers":[92,150],"times":[96],"using":[97,110],"data":[100],"conduct":[102],"with":[104],"aggregated":[105],"outputs.":[106],"We":[107],"conducted":[108],"experiments":[109,122],"two":[111],"tabular":[112],"datasets":[113],"regression":[115],"tasks":[116],"three":[118],"representative":[119],"Our":[121],"show":[123],"outputting":[125],"more":[126],"poses":[134],"a":[135],"higher":[136],"risk.":[138],"found":[141],"may":[146],"underestimated":[148],"if":[149],"exploiting":[151],"queries":[153],"are":[154],"not":[155],"assumed.":[156]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}