{"id":"https://openalex.org/W4404314376","doi":"https://doi.org/10.1145/3689217.3690615","title":"Mitigating Unauthorized Speech Synthesis for Voice Protection","display_name":"Mitigating Unauthorized Speech Synthesis for Voice Protection","publication_year":2023,"publication_date":"2023-11-19","ids":{"openalex":"https://openalex.org/W4404314376","doi":"https://doi.org/10.1145/3689217.3690615"},"language":"en","primary_location":{"id":"doi:10.1145/3689217.3690615","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3689217.3690615","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st ACM Workshop on Large AI Systems and Models with Privacy and Safety Analysis","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.20742","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100643314","display_name":"Zhisheng Zhang","orcid":"https://orcid.org/0009-0005-3301-776X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhisheng Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109774348","display_name":"Qianyi Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianyi Yang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081805488","display_name":"Derui Wang","orcid":"https://orcid.org/0000-0003-1388-7715"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Derui Wang","raw_affiliation_strings":["CSIRO's Data61, Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"CSIRO's Data61, Melbourne, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109778712","display_name":"Pengyang Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengyang Huang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101580401","display_name":"Yuxin Cao","orcid":"https://orcid.org/0000-0002-0584-7257"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuxin Cao","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103054783","display_name":"Kai Ye","orcid":"https://orcid.org/0009-0004-2177-5531"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kai Ye","raw_affiliation_strings":["The University of Hong Kong, Hong Kong, China","The University of Hong Kong, Hong Kong SAR, China"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"The University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042001449","display_name":"Jie Hao","orcid":"https://orcid.org/0000-0003-2032-665X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Hao","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100643314"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.8698,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80152698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"13","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983000159263611,"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/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7962913513183594},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7162278890609741},{"id":"https://openalex.org/keywords/spoofing-attack","display_name":"Spoofing attack","score":0.6887035965919495},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6369696855545044},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5709262490272522},{"id":"https://openalex.org/keywords/transferability","display_name":"Transferability","score":0.5610809326171875},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.49313730001449585},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4363178014755249},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.42041391134262085},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3576836585998535},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.24727243185043335},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21610182523727417}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7962913513183594},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7162278890609741},{"id":"https://openalex.org/C167900197","wikidata":"https://www.wikidata.org/wiki/Q11081100","display_name":"Spoofing attack","level":2,"score":0.6887035965919495},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6369696855545044},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5709262490272522},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.5610809326171875},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.49313730001449585},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4363178014755249},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.42041391134262085},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3576836585998535},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.24727243185043335},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21610182523727417},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3689217.3690615","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3689217.3690615","pdf_url":null,"source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st ACM Workshop on Large AI Systems and Models with Privacy and Safety Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.20742","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.20742","pdf_url":"https://arxiv.org/pdf/2410.20742","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.20742","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.20742","pdf_url":"https://arxiv.org/pdf/2410.20742","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.8399999737739563,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2376276132","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G5517038434","display_name":null,"funder_award_id":"2020YFB","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5555541602","display_name":null,"funder_award_id":"B18054","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6736261306","display_name":null,"funder_award_id":"2020YFB1805400","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G7463024246","display_name":null,"funder_award_id":"2020YFB1805400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G8951484681","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404314376.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W569478347","https://openalex.org/W1494198834","https://openalex.org/W1576227399","https://openalex.org/W2134973740","https://openalex.org/W2747874407","https://openalex.org/W2767052532","https://openalex.org/W2903739847","https://openalex.org/W2936774411","https://openalex.org/W2963300588","https://openalex.org/W2964243274","https://openalex.org/W2972848589","https://openalex.org/W3026874504","https://openalex.org/W3034635067","https://openalex.org/W3092028330","https://openalex.org/W3095232705","https://openalex.org/W3142087749","https://openalex.org/W3194668998","https://openalex.org/W3196001064","https://openalex.org/W3211329195","https://openalex.org/W4225288420","https://openalex.org/W4301420498","https://openalex.org/W4311737082","https://openalex.org/W4312743281","https://openalex.org/W4372270423","https://openalex.org/W4376163495","https://openalex.org/W4388856757","https://openalex.org/W4389279190","https://openalex.org/W4399485371"],"related_works":["https://openalex.org/W4294437891","https://openalex.org/W4226389478","https://openalex.org/W4297792928","https://openalex.org/W4221161333","https://openalex.org/W3113108043","https://openalex.org/W2061278248","https://openalex.org/W4298202768","https://openalex.org/W1914348842","https://openalex.org/W2331222812","https://openalex.org/W2294013337"],"abstract_inverted_index":{"With":[0],"just":[1],"a":[2,12],"few":[3],"speech":[4,46,74,108,164],"samples,":[5],"it":[6,39,181],"is":[7,40,75],"possible":[8],"to":[9,42,82,110,144,162,182],"perfectly":[10],"replicate":[11],"speaker's":[13],"voice":[14,20,170],"in":[15,34,67],"recent":[16],"years,":[17],"while":[18],"malicious":[19],"exploitation":[21],"(":[22],"e.g.,":[23],"telecom":[24],"fraud":[25],"for":[26,117],"illegal":[27],"financial":[28],"gain)":[29],"has":[30],"brought":[31],"huge":[32],"hazards":[33],"our":[35,147,185],"daily":[36],"lives.":[37],"Therefore,":[38],"crucial":[41],"protect":[43],"publicly":[44],"accessible":[45],"data":[47,193],"that":[48,101,123],"contains":[49],"sensitive":[50],"information,":[51],"such":[52],"as":[53],"personal":[54],"voiceprints.":[55],"Most":[56],"previous":[57],"defense":[58],"methods":[59],"have":[60],"focused":[61],"on":[62,106,134,173],"spoofing":[63],"speaker":[64],"verification":[65],"systems":[66],"timbre":[68],"similarity":[69],"but":[70],"the":[71,83,163],"synthesized":[72],"deepfake":[73,125],"still":[76],"of":[77,167],"high":[78],"quality.":[79],"In":[80],"response":[81],"rising":[84],"hazards,":[85],"we":[86],"devise":[87],"an":[88],"effective,":[89],"transferable,":[90],"and":[91,141,156,192],"robust":[92],"proactive":[93],"protection":[94],"technology":[95],"named":[96],"Pivotal":[97],"Objective":[98],"Perturbation":[99],"(POP)":[100],"applies":[102],"imperceptible":[103],"error-minimizing":[104],"noises":[105],"original":[107],"samples":[109,174,178],"prevent":[111],"them":[112],"from":[113,169],"being":[114],"effectively":[115],"learned":[116],"text-to-speech":[118],"(TTS)":[119],"synthesis":[120],"models":[121,138],"so":[122],"high-quality":[124],"speeches":[126],"cannot":[127],"be":[128],"generated.":[129],"We":[130],"conduct":[131],"extensive":[132],"experiments":[133],"state-of-the-art":[135],"(SOTA)":[136],"TTS":[137],"utilizing":[139],"objective":[140],"subjective":[142],"metrics":[143],"comprehensively":[145],"evaluate":[146],"proposed":[148],"method.":[149],"The":[150],"experimental":[151],"results":[152],"demonstrate":[153],"outstanding":[154],"effectiveness":[155],"transferability":[157],"across":[158],"various":[159],"models.":[160],"Compared":[161],"unclarity":[165],"score":[166],"21.94%":[168],"synthesizers":[171],"trained":[172],"without":[175],"protection,":[176],"POP-protected":[177],"significantly":[179],"increase":[180],"127.31%.":[183],"Moreover,":[184],"method":[186],"shows":[187],"robustness":[188],"against":[189],"noise":[190],"reduction":[191],"augmentation":[194],"techniques,":[195],"thereby":[196],"greatly":[197],"reducing":[198],"potential":[199],"hazards.":[200]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}