{"id":"https://openalex.org/W7138109204","doi":"https://doi.org/10.1609/aaai.v40i1.37002","title":"VoiceCloak: A Multi-Dimensional Defense Framework Against Unauthorized Diffusion-Based Voice Cloning","display_name":"VoiceCloak: A Multi-Dimensional Defense Framework Against Unauthorized Diffusion-Based Voice Cloning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138109204","doi":"https://doi.org/10.1609/aaai.v40i1.37002"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i1.37002","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i1.37002","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37002/40964","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37002/40964","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112742675","display_name":"Qianyue Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qianyue Hu","raw_affiliation_strings":["SUN YAT-SEN UNIVERSITY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SUN YAT-SEN UNIVERSITY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101741885","display_name":"Junyan Wu","orcid":"https://orcid.org/0000-0001-7101-7027"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junyan Wu","raw_affiliation_strings":["SUN YAT-SEN UNIVERSITY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SUN YAT-SEN UNIVERSITY","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129746745","display_name":"Wei Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Lu","raw_affiliation_strings":["SUN YAT-SEN UNIVERSITY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SUN YAT-SEN UNIVERSITY","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129731263","display_name":"Xiangyang Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I169689159","display_name":"PLA Information Engineering University","ror":"https://ror.org/00mm1qk40","country_code":"CN","type":"education","lineage":["https://openalex.org/I169689159"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyang Luo","raw_affiliation_strings":["Information Engineering University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Engineering University","institution_ids":["https://openalex.org/I169689159"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28822412,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"1","first_page":"399","last_page":"407"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.76419997215271,"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":0.76419997215271,"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":0.09969999641180038,"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":0.023399999365210533,"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/identity","display_name":"Identity (music)","score":0.565500020980835},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.503000020980835},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.46369999647140503},{"id":"https://openalex.org/keywords/cloning","display_name":"Cloning (programming)","score":0.4521999955177307},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4447999894618988},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.435699999332428},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4341999888420105}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.699400007724762},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.565500020980835},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.503000020980835},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.46369999647140503},{"id":"https://openalex.org/C121050878","wikidata":"https://www.wikidata.org/wiki/Q5135020","display_name":"Cloning (programming)","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.435699999332428},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4341999888420105},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.4023999869823456},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.29600000381469727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2881999909877777},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27160000801086426},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C522325796","wikidata":"https://www.wikidata.org/wiki/Q471880","display_name":"Identity theft","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i1.37002","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i1.37002","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37002/40964","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i1.37002","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i1.37002","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37002/40964","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7902866005897522,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138109204.pdf","grobid_xml":"https://content.openalex.org/works/W7138109204.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"Models":[1],"(DMs)":[2],"have":[3,37],"achieved":[4],"remarkable":[5],"success":[6,205],"in":[7,74,219],"realistic":[8],"voice":[9,210],"cloning":[10,98],"(VC),":[11],"while":[12],"they":[13,36],"also":[14],"increase":[15],"the":[16,32,45,64,97,105,146,161,172,177],"risk":[17],"of":[18,49,66,148,179,215],"malicious":[19],"misuse.":[20],"Existing":[21],"proactive":[22,60],"defenses":[23],"designed":[24],"for":[25,154],"traditional":[26],"VC":[27],"models":[28],"aim":[29],"to":[30,44,87,95,109,123,159,169,188],"disrupt":[31,96,189],"forgery":[33],"process,":[34],"but":[35],"been":[38],"proven":[39],"incompatible":[40],"with":[41,63],"DMs":[42],"due":[43],"intricate":[46],"generative":[47],"mechanisms":[48],"diffusion.":[50],"To":[51,78],"bridge":[52],"this":[53],"gap,":[54],"we":[55,82],"introduce":[56],"VoiceCloak,":[57],"a":[58,84],"multi-dimensional":[59],"defense":[61,204],"framework":[62],"goal":[65],"obfuscating":[67],"speaker":[68,111,116],"identity":[69,117,125],"and":[70],"degrading":[71,196],"perceptual":[72],"quality":[73],"potential":[75],"unauthorized":[76,208],"VC.":[77],"achieve":[79],"these":[80],"goals,":[81],"conduct":[83],"focused":[85],"analysis":[86],"identify":[88],"specific":[89],"vulnerabilities":[90],"within":[91],"DMs,":[92,195],"allowing":[93],"VoiceCloak":[94,113,135,164,216],"process":[99],"by":[100,118,130,194],"introducing":[101],"adversarial":[102],"perturbations":[103],"into":[104],"reference":[106],"audio.":[107],"Specifically,":[108],"obfuscate":[110],"identity,":[112],"first":[114],"targets":[115],"distorting":[119],"representation":[120],"learning":[121],"embeddings":[122],"maximize":[124],"variation,":[126],"which":[127],"is":[128,185],"guided":[129],"auditory":[131],"perception":[132],"principles.":[133],"Additionally,":[134],"disrupts":[136],"crucial":[137],"conditional":[138],"guidance":[139],"processes,":[140],"particularly":[141],"attention":[142],"context,":[143],"thereby":[144],"preventing":[145],"alignment":[147],"vocal":[149],"characteristics":[150],"that":[151],"are":[152,217],"essential":[153],"achieving":[155],"convincing":[156],"cloning.":[157,211],"Then,":[158],"address":[160],"second":[162],"objective,":[163],"introduces":[165],"score":[166],"magnitude":[167],"amplification":[168],"actively":[170],"steer":[171],"reverse":[173],"trajectory":[174],"away":[175],"from":[176],"generation":[178],"high-quality":[180],"speech.":[181],"Noise-guided":[182],"semantic":[183],"corruption":[184],"further":[186],"employed":[187],"structural":[190],"speech":[191],"semantics":[192],"captured":[193],"output":[197],"quality.":[198],"Extensive":[199],"experiments":[200],"highlight":[201],"VoiceCloak's":[202],"outstanding":[203],"rate":[206],"against":[207],"diffusion-based":[209],"Additional":[212],"audio":[213],"samples":[214],"available":[218],"demo":[220],"pages.":[221]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}
