{"id":"https://openalex.org/W4416250932","doi":"https://doi.org/10.1109/waspaa66052.2025.11230920","title":"VoxATtack: A Multimodal Attack on Voice Anonymization Systems","display_name":"VoxATtack: A Multimodal Attack on Voice Anonymization Systems","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250932","doi":"https://doi.org/10.1109/waspaa66052.2025.11230920"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5040705553","display_name":"Ahmad Aloradi","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Ahmad Aloradi","raw_affiliation_strings":["FAU Erlangen-Nürnberg,Department of Data Science,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAU Erlangen-Nürnberg,Department of Data Science,Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019098450","display_name":"\u00dcnal Ege Gaznepoglu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"\u00dcnal Ege Gaznepoglu","raw_affiliation_strings":["FAU Erlangen-Nürnberg,International Audio Laboratories Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAU Erlangen-Nürnberg,International Audio Laboratories Erlangen,Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031626756","display_name":"Emanu\u00ebl A. P. Habets","orcid":"https://orcid.org/0000-0002-2613-8046"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Emanu\u00ebl A. P. Habets","raw_affiliation_strings":["FAU Erlangen-Nürnberg,International Audio Laboratories Erlangen,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAU Erlangen-Nürnberg,International Audio Laboratories Erlangen,Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026483039","display_name":"Daniel Tenbrinck","orcid":"https://orcid.org/0000-0002-4788-9332"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Tenbrinck","raw_affiliation_strings":["FAU Erlangen-Nürnberg,Department of Data Science,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FAU Erlangen-Nürnberg,Department of Data Science,Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040705553"],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17575415,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.3772999942302704,"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":0.3772999942302704,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.19419999420642853,"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/T10863","display_name":"Voice and Speech Disorders","score":0.12110000103712082,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7368999719619751},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4706000089645386},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.44269999861717224},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.43309998512268066},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.38029998540878296},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.3100999891757965},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3050999939441681}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8098000288009644},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7368999719619751},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5551999807357788},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46050000190734863},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.44269999861717224},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.43309998512268066},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41029998660087585},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.38029998540878296},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30250000953674316},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.2612000107765198},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230920","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230920","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309618","display_name":"Ministry of Science and Technology","ror":"https://ror.org/02b207r52"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2747165665","https://openalex.org/W2808631503","https://openalex.org/W2936774411","https://openalex.org/W2951082691","https://openalex.org/W2964054038","https://openalex.org/W3010925296","https://openalex.org/W3024869864","https://openalex.org/W3043999252","https://openalex.org/W3205878676","https://openalex.org/W3209984917","https://openalex.org/W4210970267","https://openalex.org/W4385823432","https://openalex.org/W4400678062","https://openalex.org/W4408345624","https://openalex.org/W4408345627","https://openalex.org/W4408352614","https://openalex.org/W4408353477","https://openalex.org/W4408353589","https://openalex.org/W4408354634","https://openalex.org/W4408355173","https://openalex.org/W4415433670"],"related_works":[],"abstract_inverted_index":{"Voice":[0],"anonymization":[1,61,215],"systems":[2],"aim":[3],"to":[4,32,59,177,225],"protect":[5],"speaker":[6,70],"privacy":[7],"by":[8],"obscuring":[9],"vocal":[10],"traits":[11],"while":[12],"preserving":[13],"the":[14,86,108,136,144,222],"linguistic":[15,24],"content":[16],"relevant":[17],"for":[18],"downstream":[19],"applications.":[20],"However,":[21],"because":[22],"these":[23],"cues":[25],"remain":[26],"intact,":[27],"they":[28],"can":[29],"be":[30],"exploited":[31],"identify":[33],"semantic":[34],"speech":[35,102,167],"patterns":[36],"associated":[37],"with":[38,81,97],"specific":[39],"speakers.":[40],"In":[41],"this":[42],"work,":[43],"we":[44,75,164],"present":[45],"VoxATtack,":[46],"a":[47,82,94,104,128],"novel":[48],"multimodal":[49],"de-anonymization":[50],"model":[51,92],"that":[52,77,201],"incorporates":[53],"both":[54],"acoustic":[55],"and":[56,103,119,158,168,187,195,205,217],"textual":[57,79,203],"information":[58,80,204],"attack":[60],"systems.":[62],"While":[63],"previous":[64],"research":[65],"has":[66],"focused":[67],"on":[68,123,127,135,147,180,193],"refining":[69],"representations":[71],"extracted":[72],"from":[73],"speech,":[74],"show":[76],"incorporating":[78,202],"standard":[83],"ECAPA-TDNN":[84,99],"improves":[85],"attacker\u2019s":[87],"performance.":[88],"Our":[89,198],"proposed":[90],"VoxATtack":[91,176],"employs":[93],"dual-branch":[95],"architecture,":[96],"an":[98],"processing":[100],"anonymized":[101,166],"pretrained":[105],"BERT":[106],"encoding":[107],"transcriptions.":[109],"Both":[110],"outputs":[111],"are":[112],"projected":[113],"into":[114],"embeddings":[115],"of":[116,150],"equal":[117,190],"dimensionality":[118],"then":[120],"fused":[121],"based":[122],"confidence":[124],"weights":[125],"computed":[126],"per-utterance":[129],"basis.":[130],"When":[131],"evaluating":[132],"our":[133],"approach":[134],"VoicePrivacy":[137],"Attacker":[138],"Challenge":[139],"(VPAC)":[140],"dataset,":[141],"it":[142],"outperforms":[143],"top-ranking":[145],"attackers":[146],"five":[148],"out":[149],"seven":[151],"benchmarks,":[152,183],"namely":[153],"B3,":[154],"B4,":[155],"B5,":[156],"T8-5,":[157],"T12-5.":[159],"To":[160],"further":[161],"boost":[162],"performance,":[163],"leverage":[165],"SpecAugment":[169],"as":[170],"augmentation":[171,208],"techniques.":[172],"This":[173],"enhancement":[174],"enables":[175],"achieve":[178],"state-of-the-art":[179],"all":[181],"VPAC":[182],"after":[184],"scoring":[185],"20.6%":[186],"27.2%":[188],"average":[189],"error":[191],"rate":[192],"T10-2":[194],"T25-1,":[196],"respectively.":[197],"results":[199],"demonstrate":[200],"selective":[206],"data":[207],"reveals":[209],"critical":[210],"vulnerabilities":[211],"in":[212,221],"current":[213],"voice":[214],"methods":[216],"exposes":[218],"potential":[219],"weaknesses":[220],"datasets":[223],"used":[224],"evaluate":[226],"them.":[227]},"counts_by_year":[],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-11-14T00:00:00"}