{"id":"https://openalex.org/W4408281803","doi":"https://doi.org/10.1109/tifs.2025.3550068","title":"GLiRA: Closed-Box Membership Inference Attack via Knowledge Distillation","display_name":"GLiRA: Closed-Box Membership Inference Attack via Knowledge Distillation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408281803","doi":"https://doi.org/10.1109/tifs.2025.3550068"},"language":"en","primary_location":{"id":"doi:10.1109/tifs.2025.3550068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2025.3550068","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-article"},"type":"article","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/A5092698837","display_name":"Andrey V. Galichin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrey V. Galichin","raw_affiliation_strings":["Artificial Intelligence Research Institute, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute, Moscow, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mikhail Pautov","orcid":"https://orcid.org/0000-0003-0438-6361"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mikhail Pautov","raw_affiliation_strings":["Artificial Intelligence Research Institute, Moscow, Russia"],"raw_orcid":"https://orcid.org/0000-0003-0438-6361","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute, Moscow, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098316666","display_name":"Alexey Zhavoronkin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexey Zhavoronkin","raw_affiliation_strings":["Sber, Moscow, Russia","Sber, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sber, Moscow, Russia","institution_ids":[]},{"raw_affiliation_string":"Sber, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048793164","display_name":"Oleg Y. Rogov","orcid":"https://orcid.org/0000-0001-9672-2427"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oleg Y. Rogov","raw_affiliation_strings":["Artificial Intelligence Research Institute, Moscow, Russia"],"raw_orcid":"https://orcid.org/0000-0001-9672-2427","affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute, Moscow, Russia","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004111307","display_name":"Ivan Oseledets","orcid":"https://orcid.org/0000-0003-2071-2163"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Oseledets","raw_affiliation_strings":["Artificial Intelligence Research Institute, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Institute, Moscow, Russia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.98,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96308676,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"20","issue":null,"first_page":"3893","last_page":"3906"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9226999878883362,"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":0.9226999878883362,"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/computer-science","display_name":"Computer science","score":0.8117644786834717},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6811696887016296},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.5648642182350159},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4554848074913025},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4217895269393921},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.40758460760116577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3087230324745178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8117644786834717},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6811696887016296},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.5648642182350159},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4554848074913025},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4217895269393921},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.40758460760116577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3087230324745178},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tifs.2025.3550068","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2025.3550068","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2194775991","https://openalex.org/W2473418344","https://openalex.org/W2535690855","https://openalex.org/W2566079294","https://openalex.org/W2795435272","https://openalex.org/W2930926105","https://openalex.org/W2963140444","https://openalex.org/W2963163009","https://openalex.org/W2964137095","https://openalex.org/W2982157312","https://openalex.org/W3138815606","https://openalex.org/W3187295906","https://openalex.org/W3214437258","https://openalex.org/W4250482878","https://openalex.org/W4288057780","https://openalex.org/W4308410483","https://openalex.org/W4308410741","https://openalex.org/W4385565597","https://openalex.org/W4385696518","https://openalex.org/W4394625755","https://openalex.org/W4401023728"],"related_works":["https://openalex.org/W2047881532","https://openalex.org/W4389072557","https://openalex.org/W2055243143","https://openalex.org/W4319452366","https://openalex.org/W3026162553","https://openalex.org/W4293695278","https://openalex.org/W3013663659","https://openalex.org/W2727407240","https://openalex.org/W3197218948","https://openalex.org/W2141612310"],"abstract_inverted_index":{"While":[0],"Deep":[1],"Neural":[2],"Networks":[3],"demonstrate":[4,162],"remarkable":[5],"performance":[6],"in":[7,176],"practical":[8],"tasks,":[9],"they":[10],"are":[11,67],"vulnerable":[12],"to":[13,25,42,54,112,145],"membership":[14,32,57,102,113,130,173],"inference":[15,33,103,114,131,174],"attacks":[16,175],"aimed":[17],"at":[18],"identifying":[19],"whether":[20],"a":[21,31,36,44,51,108,127],"certain":[22],"object":[23],"belongs":[24],"the":[26,56,60,73,80,83,88,92,97,119,124,134,137,150,170,177],"training":[27,89],"dataset.":[28],"To":[29,95],"conduct":[30,50],"attack":[34,132,168],"on":[35],"target":[37,74,84,138],"model,":[38],"an":[39,146],"adversary":[40],"has":[41],"train":[43],"set":[45],"of":[46,59,82,91,99,126,136,179],"shadow":[47,65,93,100],"models":[48,66],"and":[49,143,158,161],"statistical":[52],"test":[53],"determine":[55],"status":[58],"particular":[61],"input":[62],"object.":[63],"Usually,":[64],"trained":[68],"without":[69],"taking":[70],"into":[71],"account":[72],"model;":[75],"we":[76,105],"argue":[77],"that":[78,118,163],"utilizing":[79],"predictions":[81],"model":[85,139,159],"can":[86],"guide":[87],"process":[90],"model.":[94],"improve":[96],"efficiency":[98,125],"model-based":[101],"attacks,":[104],"propose":[106],"GLiRA,":[107],"knowledge":[109,120,164],"distillation-guided":[110,165],"approach":[111],"attacks.":[115],"We":[116,148],"observe":[117],"distillation":[121],"significantly":[122],"improves":[123],"likelihood":[128,166],"ratio":[129,167],"when":[133],"architecture":[135],"is":[140],"both":[141],"known":[142],"unknown":[144],"attacker.":[147],"evaluate":[149],"proposed":[151],"method":[152],"across":[153],"multiple":[154],"image":[155],"classification":[156],"datasets":[157],"architectures":[160],"outperforms":[169],"current":[171],"state-of-the-art":[172],"majority":[178],"experimental":[180],"settings.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-03-11T00:00:00"}