{"id":"https://openalex.org/W4416798531","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249369","title":"Transferability of Adversarial Examples Across Speaker Embedding Models for Voice Privacy Protection","display_name":"Transferability of Adversarial Examples Across Speaker Embedding Models for Voice Privacy Protection","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798531","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249369"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5073020291","display_name":"Kotaro Nakamura","orcid":null},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kotaro Nakamura","raw_affiliation_strings":["The University of Electro-Communications,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005264920","display_name":"Takuya Takahashi","orcid":"https://orcid.org/0000-0001-6523-0622"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Takahashi","raw_affiliation_strings":["The University of Electro-Communications,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Japan","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041887072","display_name":"Toru Nakashika","orcid":"https://orcid.org/0000-0003-1863-6771"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toru Nakashika","raw_affiliation_strings":["The University of Electro-Communications,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Electro-Communications,Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I20529979"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34428588,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2104","last_page":"2109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.3253999948501587,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.3253999948501587,"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/T10860","display_name":"Speech and Audio Processing","score":0.14830000698566437,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.10409999638795853,"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/adversarial-system","display_name":"Adversarial system","score":0.802299976348877},{"id":"https://openalex.org/keywords/transferability","display_name":"Transferability","score":0.6969000101089478},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6383000016212463},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5569999814033508},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5152000188827515},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.49149999022483826},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.4325000047683716},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4320000112056732}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.802299976348877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.698199987411499},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.6969000101089478},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6383000016212463},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6256999969482422},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5569999814033508},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5152000188827515},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.49149999022483826},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4325000047683716},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4320000112056732},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4000000059604645},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.3741999864578247},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.33559998869895935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3327000141143799},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2793000042438507},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C2776788033","wikidata":"https://www.wikidata.org/wiki/Q320769","display_name":"Eavesdropping","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C150817343","wikidata":"https://www.wikidata.org/wiki/Q875932","display_name":"Digital watermarking","level":3,"score":0.25519999861717224},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4728209639","display_name":null,"funder_award_id":"24H00715","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"}],"funders":[{"id":"https://openalex.org/F4320320212","display_name":"Japan Society for the Promotion of Science London","ror":"https://ror.org/02m7axw05"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2890964092","https://openalex.org/W2963542245","https://openalex.org/W2963857521","https://openalex.org/W2964058413","https://openalex.org/W2972359262","https://openalex.org/W3015811740","https://openalex.org/W3024869864","https://openalex.org/W3205878676","https://openalex.org/W4232378273","https://openalex.org/W4402111485","https://openalex.org/W4402112632"],"related_works":[],"abstract_inverted_index":{"The":[0,76,122],"widespread":[1],"use":[2],"of":[3,23,68,81],"speaker":[4,44,82],"identification":[5,98],"technology":[6,187],"has":[7],"raised":[8],"concerns":[9],"regarding":[10],"personal":[11],"information":[12],"contained":[13],"in":[14,127],"voice":[15,18,189],"data,":[16],"particularly":[17],"privacy.":[19],"While":[20],"the":[21,34,66,73,101,147],"application":[22],"adversarial":[24,69,169],"attacks":[25,130],"is":[26,41,55],"a":[27,154,175,186],"potential":[28],"protection":[29],"measure":[30],"for":[31,188],"this":[32,61],"issue,":[33],"extent":[35],"to":[36,135],"which":[37,111,118],"their":[38],"attack":[39,95,158],"effectiveness":[40,96,184],"maintained":[42],"across":[43],"embedding":[45,83],"extractors":[46,84],"with":[47,85],"different":[48,86],"architectures":[49],"(a":[50],"property":[51],"known":[52],"as":[53,185],"transferability)":[54],"not":[56,173],"yet":[57],"well":[58],"understood.":[59],"In":[60],"study,":[62],"we":[63],"experimentally":[64],"evaluated":[65,94],"transferability":[67],"audio":[70,107,161,170],"generated":[71],"using":[72,97,109],"I-FGSM":[74],"method.":[75],"evaluation":[77],"targeted":[78],"three":[79],"types":[80],"architectures:":[87],"X-vector,":[88],"Titanet,":[89],"MelStyleEncoder":[90],"and":[91,100,105,116,160],"ECAPA-TDNN.":[92],"We":[93],"accuracy":[99],"Equal":[102],"Error":[103],"Rate,":[104],"assessed":[106],"quality":[108,162],"PESQ,":[110],"predicts":[112],"subjective":[113],"listening":[114],"quality,":[115],"SI-SDR,":[117],"measures":[119],"signal":[120],"fidelity.":[121],"experimental":[123],"results":[124,166],"showed":[125],"that":[126,168],"black-box":[128],"attacks,":[129],"from":[131],"models":[132],"like":[133],"X-vector":[134],"ECAPA-TDNN":[136],"exhibited":[137],"high":[138],"transferability,":[139],"while":[140],"an":[141],"asymmetrical":[142],"relationship":[143],"was":[144,163],"observed":[145],"where":[146],"reverse":[148],"direction":[149],"had":[150],"low":[151],"transferability.":[152],"Furthermore,":[153],"clear":[155],"tradeoff":[156],"between":[157],"strength":[159],"confirmed.":[164],"These":[165],"indicate":[167],"can":[171],"affect":[172],"only":[174],"single":[176],"model":[177],"but":[178],"also":[179],"other":[180],"models,":[181],"suggesting":[182],"its":[183],"privacy":[190],"protection.":[191]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}