{"id":"https://openalex.org/W3093077017","doi":"https://doi.org/10.1145/3394171.3413716","title":"DeepSonar: Towards Effective and Robust Detection of AI-Synthesized Fake Voices","display_name":"DeepSonar: Towards Effective and Robust Detection of AI-Synthesized Fake Voices","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093077017","doi":"https://doi.org/10.1145/3394171.3413716","mag":"3093077017"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3413716","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=8085&amp;amp;context=sis_research","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100614000","display_name":"Run Wang","orcid":"https://orcid.org/0000-0002-2842-5137"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Run Wang","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034751153","display_name":"Felix Juefei-Xu","orcid":"https://orcid.org/0000-0002-0857-8611"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Felix Juefei-Xu","raw_affiliation_strings":["Alibaba Group, San Mateo, CA, USA"],"affiliations":[{"raw_affiliation_string":"Alibaba Group, San Mateo, CA, USA","institution_ids":["https://openalex.org/I4210095624"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036183844","display_name":"Yihao Huang","orcid":"https://orcid.org/0000-0002-5784-770X"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihao Huang","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026239594","display_name":"Qing Guo","orcid":"https://orcid.org/0000-0003-0974-9299"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Qing Guo","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084396416","display_name":"Xiaofei Xie","orcid":"https://orcid.org/0000-0002-1288-6502"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiaofei Xie","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101468661","display_name":"Lei Ma","orcid":"https://orcid.org/0000-0002-8621-2420"},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Lei Ma","raw_affiliation_strings":["Kyushu University, Fukuoka, Japan"],"affiliations":[{"raw_affiliation_string":"Kyushu University, Fukuoka, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100355692","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0001-7300-9215"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Nanyang Technology University &amp; Zhejiang University, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technology University &amp; Zhejiang University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5100614000"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":8.2534,"has_fulltext":false,"cited_by_count":114,"citation_normalized_percentile":{"value":0.98076408,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1207","last_page":"1216"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973999857902527,"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":0.9973999857902527,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9947999715805054,"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":0.7966023683547974},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7301087379455566},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6861909627914429},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5985981822013855},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5210734605789185},{"id":"https://openalex.org/keywords/constant-false-alarm-rate","display_name":"Constant false alarm rate","score":0.46492505073547363},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42321985960006714},{"id":"https://openalex.org/keywords/voice-command-device","display_name":"Voice command device","score":0.422894686460495},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3734734058380127},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36723792552948}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7966023683547974},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7301087379455566},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6861909627914429},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5985981822013855},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5210734605789185},{"id":"https://openalex.org/C77052588","wikidata":"https://www.wikidata.org/wiki/Q644307","display_name":"Constant false alarm rate","level":2,"score":0.46492505073547363},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42321985960006714},{"id":"https://openalex.org/C178718744","wikidata":"https://www.wikidata.org/wiki/Q2350070","display_name":"Voice command device","level":2,"score":0.422894686460495},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3734734058380127},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36723792552948},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3394171.3413716","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3413716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-8085","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=8085&amp;amp;context=sis_research","pdf_url":null,"source":{"id":"https://openalex.org/S4377196871","display_name":"Institutional Knowledge (InK) - Institutional Knowledge at Singapore Management University (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1145/3394171.3413716","raw_type":"Conference Proceeding Article"}],"best_oa_location":{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-8085","is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=8085&amp;amp;context=sis_research","pdf_url":null,"source":{"id":"https://openalex.org/S4377196871","display_name":"Institutional Knowledge (InK) - Institutional Knowledge at Singapore Management University (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://doi.org/10.1145/3394171.3413716","raw_type":"Conference Proceeding Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1548535091","https://openalex.org/W1570629387","https://openalex.org/W1579853615","https://openalex.org/W1591117985","https://openalex.org/W1915485278","https://openalex.org/W1945616565","https://openalex.org/W2041127133","https://openalex.org/W2045158511","https://openalex.org/W2137782235","https://openalex.org/W2473388484","https://openalex.org/W2507387377","https://openalex.org/W2571081683","https://openalex.org/W2616028256","https://openalex.org/W2697504846","https://openalex.org/W2738406145","https://openalex.org/W2799640043","https://openalex.org/W2800289214","https://openalex.org/W2804337238","https://openalex.org/W2898868990","https://openalex.org/W2922015121","https://openalex.org/W2936802426","https://openalex.org/W2947133760","https://openalex.org/W2957905354","https://openalex.org/W2963035245","https://openalex.org/W2963178695","https://openalex.org/W2963609956","https://openalex.org/W2963658876","https://openalex.org/W2963684180","https://openalex.org/W2964243274","https://openalex.org/W2967606780","https://openalex.org/W2984529706","https://openalex.org/W2986844069","https://openalex.org/W3034214108","https://openalex.org/W3034900344","https://openalex.org/W3035574324","https://openalex.org/W3038930935","https://openalex.org/W3092997524","https://openalex.org/W3096651815","https://openalex.org/W3099444373","https://openalex.org/W3125803510","https://openalex.org/W4229494842","https://openalex.org/W4253525579"],"related_works":["https://openalex.org/W2388326001","https://openalex.org/W2998914036","https://openalex.org/W2770593030","https://openalex.org/W3154990682","https://openalex.org/W3210882018","https://openalex.org/W2970990331","https://openalex.org/W4379116102","https://openalex.org/W3207178610","https://openalex.org/W3211782752","https://openalex.org/W4309864825"],"abstract_inverted_index":{"With":[0],"the":[1,96,116,130,170],"recent":[2],"advances":[3],"in":[4,42,139,188,244],"voice":[5,204],"synthesis,":[6],"AI-synthesized":[7,83,136],"fake":[8,38,84,137,190],"voices":[9,39],"are":[10,17,40,46,101,150],"indistinguishable":[11],"to":[12,19,28,49,81,93,144,168],"human":[13],"ears":[14],"and":[15,22,33,45,108,135,165,177,206,223,238],"widely":[16,102],"applied":[18],"produce":[20],"realistic":[21],"natural":[23],"DeepFakes,":[24],"exhibiting":[25],"real":[26,134],"threats":[27],"our":[29],"society.":[30],"However,":[31],"effective":[32,222],"robust":[34,224],"detectors":[35],"for":[36,104,221],"synthesized":[37],"still":[41],"their":[43],"infancy":[44],"not":[47],"ready":[48],"fully":[50],"tackle":[51],"this":[52,56,112],"emerging":[53],"threat.":[54],"In":[55,111],"paper,":[57],"we":[58,114],"devise":[59],"a":[60,76,124,141,214],"novel":[61],"approach,":[62],"named":[63],"DeepSonar,":[64],"based":[65],"on":[66,152],"monitoring":[67],"neuron":[68,87,120,219],"behaviors":[69,88,220],"of":[70,118,186,235],"speaker":[71],"recognition":[72],"(SR)":[73],"system,":[74],"i.e.,":[75],"deep":[77],"neural":[78],"network":[79],"(DNN),":[80],"discern":[82],"voices.":[85,191],"Layer-wise":[86],"provide":[89],"an":[90,231],"important":[91],"insight":[92,216],"meticulously":[94],"catch":[95],"differences":[97,132],"among":[98],"inputs,":[99],"which":[100],"employed":[103],"building":[105],"safety,":[106],"robust,":[107],"interpretable":[109],"DNNs.":[110],"work,":[113],"leverage":[115],"power":[117],"layer-wise":[119],"activation":[121],"patterns":[122],"with":[123],"conjecture":[125],"that":[126],"they":[127],"can":[128],"capture":[129],"subtle":[131],"between":[133],"voices,":[138],"providing":[140],"cleaner":[142],"signal":[143],"classifiers":[145],"than":[146],"raw":[147],"inputs.":[148],"Experiments":[149],"conducted":[151],"three":[153],"datasets":[154],"(including":[155],"commercial":[156],"products":[157],"from":[158],"Google,":[159],"Baidu,":[160],"etc)":[161],"containing":[162],"both":[163],"English":[164],"Chinese":[166],"languages":[167],"corroborate":[169],"high":[171],"detection":[172],"rates":[173,181],"(98.1%":[174],"average":[175],"accuracy)":[176],"low":[178],"false":[179],"alarm":[180],"(about":[182],"2%":[183],"error":[184],"rate)":[185],"DeepSonar":[187],"discerning":[189],"Furthermore,":[192],"extensive":[193],"experimental":[194],"results":[195],"also":[196],"demonstrate":[197],"its":[198],"robustness":[199],"against":[200],"manipulation":[201],"attacks":[202],"(e.g.,":[203],"conversion":[205],"additive":[207],"real-world":[208],"noises).":[209],"Our":[210],"work":[211],"further":[212],"poses":[213],"new":[215],"into":[217],"adopting":[218],"AI":[225],"aided":[226],"multimedia":[227],"fakes":[228],"forensics":[229],"as":[230],"inside-out":[232],"approach":[233],"instead":[234],"being":[236],"motivated":[237],"swayed":[239],"by":[240],"various":[241],"artifacts":[242],"introduced":[243],"synthesizing":[245],"fakes.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":27},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
