{"id":"https://openalex.org/W3047561893","doi":"https://doi.org/10.1109/infocom41043.2020.9155483","title":"Voiceprint Mimicry Attack Towards Speaker Verification System in Smart Home","display_name":"Voiceprint Mimicry Attack Towards Speaker Verification System in Smart Home","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3047561893","doi":"https://doi.org/10.1109/infocom41043.2020.9155483","mag":"3047561893"},"language":"en","primary_location":{"id":"doi:10.1109/infocom41043.2020.9155483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom41043.2020.9155483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications","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/A5100699231","display_name":"Lei Zhang","orcid":"https://orcid.org/0000-0002-2917-9652"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076583947","display_name":"Yan Meng","orcid":"https://orcid.org/0000-0001-5445-0347"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Meng","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008395330","display_name":"Jiahao Yu","orcid":"https://orcid.org/0009-0006-0306-0932"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahao Yu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030028368","display_name":"Chong Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chong Xiang","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059042832","display_name":"Brandon Falk","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Brandon Falk","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039106671","display_name":"Haojin Zhu","orcid":"https://orcid.org/0000-0001-5079-4556"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haojin Zhu","raw_affiliation_strings":["Shanghai Jiao Tong University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"377","last_page":"386"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9979000091552734,"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":0.9797000288963318,"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":0.794060468673706},{"id":"https://openalex.org/keywords/mimicry","display_name":"Mimicry","score":0.6992179155349731},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6945847868919373},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5534437894821167},{"id":"https://openalex.org/keywords/psychoacoustics","display_name":"Psychoacoustics","score":0.5430000424385071},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.5210729837417603},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5123923420906067},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5053010582923889},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.4950474798679352},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4817923903465271},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45103180408477783},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.4336748421192169},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.42375117540359497},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3823099136352539},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.34290003776550293},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3081333041191101}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.794060468673706},{"id":"https://openalex.org/C7863114","wikidata":"https://www.wikidata.org/wiki/Q192627","display_name":"Mimicry","level":2,"score":0.6992179155349731},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6945847868919373},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5534437894821167},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.5430000424385071},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.5210729837417603},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5123923420906067},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5053010582923889},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.4950474798679352},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4817923903465271},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45103180408477783},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.4336748421192169},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.42375117540359497},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3823099136352539},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.34290003776550293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3081333041191101},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/infocom41043.2020.9155483","is_oa":false,"landing_page_url":"https://doi.org/10.1109/infocom41043.2020.9155483","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE INFOCOM 2020 - IEEE Conference on Computer Communications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8600000143051147,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1673923490","https://openalex.org/W1945616565","https://openalex.org/W2022217943","https://openalex.org/W2043843997","https://openalex.org/W2084769044","https://openalex.org/W2114925438","https://openalex.org/W2194775991","https://openalex.org/W2486441166","https://openalex.org/W2534482106","https://openalex.org/W2570685808","https://openalex.org/W2612434969","https://openalex.org/W2624801495","https://openalex.org/W2746600820","https://openalex.org/W2751902866","https://openalex.org/W2798302089","https://openalex.org/W2808631503","https://openalex.org/W2809536883","https://openalex.org/W2890559797","https://openalex.org/W2890964092","https://openalex.org/W2953384591","https://openalex.org/W2962717526","https://openalex.org/W2962747881","https://openalex.org/W2963058500","https://openalex.org/W2963077926","https://openalex.org/W2963207607","https://openalex.org/W2963564844","https://openalex.org/W2963857521","https://openalex.org/W2964121744","https://openalex.org/W2964153729","https://openalex.org/W2964301649","https://openalex.org/W2969333443","https://openalex.org/W3049502060","https://openalex.org/W3106412272","https://openalex.org/W4300824008","https://openalex.org/W6631190155","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6713134421","https://openalex.org/W6722479552","https://openalex.org/W6731927902","https://openalex.org/W6737575990","https://openalex.org/W6748288002","https://openalex.org/W6751839145"],"related_works":["https://openalex.org/W1519490734","https://openalex.org/W2963560054","https://openalex.org/W2610449869","https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W4306406306","https://openalex.org/W2990940109","https://openalex.org/W4235705411","https://openalex.org/W204267554","https://openalex.org/W2134501921"],"abstract_inverted_index":{"The":[0,66],"advancement":[1],"of":[2,100,156,163],"voice":[3,30,59,88],"controllable":[4],"systems":[5],"(VC-Ses)":[6],"has":[7],"dramatically":[8],"affected":[9],"our":[10],"daily":[11],"lifestyle":[12],"and":[13,43,55,174],"catalyzed":[14],"the":[15,57,73,83,87,98,106,110,119,123,129,135,145,161,191],"smart":[16,53,195],"home's":[17],"deployment.":[18],"Currently,":[19],"most":[20],"VCSes":[21],"exploit":[22],"automatic":[23],"speaker":[24,131],"verification":[25],"(ASV)":[26],"to":[27,82,109,143],"prevent":[28],"various":[29],"attacks":[31],"(e.g.,":[32],"replay":[33],"attack).":[34],"In":[35],"this":[36],"study,":[37],"we":[38],"present":[39],"VMask,":[40],"a":[41,63,183],"novel":[42],"practical":[44],"voiceprint":[45],"mimicry":[46],"attack":[47],"that":[48,72],"could":[49],"fool":[50],"ASV":[51,79,120],"in":[52,86],"home":[54,196],"inject":[56],"malicious":[58],"command":[60],"disguised":[61],"as":[62,134],"legitimate":[64],"user.":[65],"key":[67],"observation":[68],"behind":[69],"VMask":[70,96,116,164],"is":[71,141],"deep":[74],"learning":[75],"models":[76],"utilized":[77],"by":[78,104,165],"are":[80],"vulnerable":[81],"subtle":[84,94,107],"perturbations":[85,108,147],"input":[89],"space.":[90],"To":[91],"generate":[92],"these":[93],"perturbations,":[95],"leverages":[97],"idea":[99],"adversarial":[101,146],"examples.":[102],"Then":[103],"adding":[105],"recordings":[111],"from":[112],"an":[113],"arbitrary":[114],"speaker,":[115],"can":[117],"mislead":[118],"into":[121],"classifying":[122],"crafted":[124],"speech":[125],"samples,":[126],"which":[127],"mirror":[128],"former":[130],"for":[132],"human,":[133],"targeted":[136],"victim.":[137],"Moreover,":[138],"psychoacoustic":[139],"masking":[140],"employed":[142],"manipulate":[144],"under":[148],"human":[149],"perception":[150],"threshold,":[151],"thus":[152],"making":[153],"victim":[154],"unaware":[155],"ongoing":[157],"attacks.":[158],"We":[159],"validate":[160],"effectiveness":[162],"performing":[166],"comprehensive":[167],"experiments":[168],"on":[169,187,194],"both":[170],"grey":[171],"box":[172,176],"(VGGVox)":[173],"black":[175],"(Microsoft":[177],"Azure":[178],"Speaker":[179],"Verification)":[180],"ASVs.":[181],"Additionally,":[182],"real-world":[184],"case":[185],"study":[186],"Apple":[188],"HomeKit":[189],"proves":[190],"VMask's":[192],"practicability":[193],"platforms.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}
