{"id":"https://openalex.org/W4410771307","doi":"https://doi.org/10.1109/icasspw65056.2025.11011198","title":"USMID: A Unimodal Speaker-Level Membership Inference Detector for Contrastive Pretraining","display_name":"USMID: A Unimodal Speaker-Level Membership Inference Detector for Contrastive Pretraining","publication_year":2025,"publication_date":"2025-04-06","ids":{"openalex":"https://openalex.org/W4410771307","doi":"https://doi.org/10.1109/icasspw65056.2025.11011198"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw65056.2025.11011198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-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/A5085789933","display_name":"Ruoxi Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I202334528","display_name":"Beijing Electronic Science and Technology Institute","ror":"https://ror.org/01xdzh226","country_code":"CN","type":"education","lineage":["https://openalex.org/I202334528"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruoxi Cheng","raw_affiliation_strings":["Beijing Electronic Science and Technology Institute,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Electronic Science and Technology Institute,Beijing,China","institution_ids":["https://openalex.org/I202334528"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100523626","display_name":"Yizhong Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I202334528","display_name":"Beijing Electronic Science and Technology Institute","ror":"https://ror.org/01xdzh226","country_code":"CN","type":"education","lineage":["https://openalex.org/I202334528"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhong Ding","raw_affiliation_strings":["Beijing Electronic Science and Technology Institute,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Electronic Science and Technology Institute,Beijing,China","institution_ids":["https://openalex.org/I202334528"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102650569","display_name":"Shuirong Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuirong Cao","raw_affiliation_strings":["AVIC Nanjing Engineering Institute of Aircraft Systems,Nanjing,China"],"affiliations":[{"raw_affiliation_string":"AVIC Nanjing Engineering Institute of Aircraft Systems,Nanjing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073038991","display_name":"Shitong Shao","orcid":"https://orcid.org/0000-0003-4689-6140"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shitong Shao","raw_affiliation_strings":["Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology (Guangzhou),Guangzhou,China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111703907","display_name":"Zhiqiang Wang","orcid":"https://orcid.org/0009-0009-2510-1522"},"institutions":[{"id":"https://openalex.org/I202334528","display_name":"Beijing Electronic Science and Technology Institute","ror":"https://ror.org/01xdzh226","country_code":"CN","type":"education","lineage":["https://openalex.org/I202334528"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiang Wang","raw_affiliation_strings":["Beijing Electronic Science and Technology Institute,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Beijing Electronic Science and Technology Institute,Beijing,China","institution_ids":["https://openalex.org/I202334528"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5085789933"],"corresponding_institution_ids":["https://openalex.org/I202334528"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05936796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9717000126838684,"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/T12031","display_name":"Speech and dialogue systems","score":0.9717000126838684,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9304999709129333,"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":0.6126484870910645},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.61030513048172},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5517426133155823},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5456346869468689},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5260558128356934},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5197786688804626},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4278474450111389},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.34924963116645813},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.05446860194206238}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6126484870910645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.61030513048172},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5517426133155823},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5456346869468689},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5260558128356934},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5197786688804626},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4278474450111389},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.34924963116645813},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.05446860194206238},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw65056.2025.11011198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw65056.2025.11011198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2366906938","https://openalex.org/W2349391998","https://openalex.org/W4205655149","https://openalex.org/W2000775715","https://openalex.org/W2055243143","https://openalex.org/W2074467390","https://openalex.org/W2795393339","https://openalex.org/W2626393719","https://openalex.org/W4390618967","https://openalex.org/W2174745845"],"abstract_inverted_index":{"Audio":[0],"can":[1,139],"disclose":[2],"PII,":[3],"particularly":[4],"when":[5],"combined":[6],"with":[7],"related":[8],"text":[9,65,115,168],"data.":[10,169],"Therefore,":[11],"it":[12],"is":[13,116,127],"essential":[14],"to":[15,18,122],"develop":[16],"tools":[17],"detect":[19],"privacy":[20],"leakage":[21],"in":[22,83,128],"Contrastive":[23],"Language-Audio":[24],"Pretraining(CLAP).":[25],"Existing":[26],"MIAs":[27],"need":[28],"audio":[29,146],"as":[30],"input,":[31],"risking":[32],"exposure":[33],"of":[34,102,112,147],"voiceprint":[35],"and":[36,67,98,158],"requiring":[37],"costly":[38],"shadow":[39,72],"models.":[40,73],"To":[41],"address":[42],"these":[43,92],"challenges,":[44],"we":[45,87],"propose":[46],"USMID,":[47],"a":[48,100],"textual":[49,77],"unimodal":[50],"speaker-level":[51],"membership":[52],"inference":[53],"detector":[54,121],"for":[55],"CLAP":[56,96,155],"models,":[57],"which":[58],"queries":[59],"the":[60,95,109,119,125,129,148],"target":[61],"model":[62,97,156],"using":[63,94,166],"only":[64,167],"data":[66],"does":[68],"not":[69,82,134],"require":[70],"training":[71,84,130],"We":[74],"randomly":[75],"generate":[76],"gibberish":[78],"that":[79,161],"are":[80],"clearly":[81],"dataset.":[85],"Then":[86],"extract":[88],"feature":[89,110],"vectors":[90],"from":[91],"texts":[93],"train":[99],"set":[101,131],"anomaly":[103,120],"detectors":[104],"on":[105,153],"them.":[106],"During":[107],"inference,":[108],"vector":[111],"each":[113],"test":[114],"input":[117],"into":[118],"determine":[123],"if":[124],"speaker":[126],"(anomalous)":[132],"or":[133],"(normal).":[135],"If":[136],"available,":[137],"USMID":[138,162],"further":[140],"enhance":[141],"detection":[142],"by":[143],"integrating":[144],"real":[145],"tested":[149],"speaker.":[150],"Extensive":[151],"experiments":[152],"various":[154],"architectures":[157],"datasets":[159],"demonstrate":[160],"outperforms":[163],"baseline":[164],"methods":[165]},"counts_by_year":[],"updated_date":"2026-02-26T08:16:20.718346","created_date":"2025-10-10T00:00:00"}