{"id":"https://openalex.org/W4200004927","doi":"https://doi.org/10.1109/pst52912.2021.9647775","title":"SegmentPerturb: Effective Black-Box Hidden Voice Attack on Commercial ASR Systems via Selective Deletion","display_name":"SegmentPerturb: Effective Black-Box Hidden Voice Attack on Commercial ASR Systems via Selective Deletion","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4200004927","doi":"https://doi.org/10.1109/pst52912.2021.9647775"},"language":"en","primary_location":{"id":"doi:10.1109/pst52912.2021.9647775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pst52912.2021.9647775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 18th International Conference on Privacy, Security and Trust (PST)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ontariotechu.scholaris.ca/bitstreams/c4682750-6e69-4fe4-8d22-75ed86d65330/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060889217","display_name":"Ganyu Wang","orcid":"https://orcid.org/0000-0002-0573-1887"},"institutions":[{"id":"https://openalex.org/I39470171","display_name":"University of Ontario Institute of Technology","ror":"https://ror.org/016zre027","country_code":"CA","type":"education","lineage":["https://openalex.org/I39470171"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Ganyu Wang","raw_affiliation_strings":["Ontario Tech University, Oshawa, Ontario"],"affiliations":[{"raw_affiliation_string":"Ontario Tech University, Oshawa, Ontario","institution_ids":["https://openalex.org/I39470171"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016781361","display_name":"Miguel Vargas Mart\u00edn","orcid":"https://orcid.org/0000-0001-8169-6836"},"institutions":[{"id":"https://openalex.org/I39470171","display_name":"University of Ontario Institute of Technology","ror":"https://ror.org/016zre027","country_code":"CA","type":"education","lineage":["https://openalex.org/I39470171"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Miguel Vargas Martin","raw_affiliation_strings":["Ontario Tech University, Oshawa, Ontario"],"affiliations":[{"raw_affiliation_string":"Ontario Tech University, Oshawa, Ontario","institution_ids":["https://openalex.org/I39470171"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060889217"],"corresponding_institution_ids":["https://openalex.org/I39470171"],"apc_list":null,"apc_paid":null,"fwci":0.1399,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58363636,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9986000061035156,"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":0.9843999743461609,"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":0.8150832056999207},{"id":"https://openalex.org/keywords/voice-command-device","display_name":"Voice command device","score":0.6944321990013123},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6329526305198669},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5126928091049194},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.49547111988067627},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.4693050682544708},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4581647515296936},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.4460488259792328},{"id":"https://openalex.org/keywords/smartwatch","display_name":"Smartwatch","score":0.4247579872608185},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33903002738952637},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2712784707546234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23802882432937622},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.18118339776992798},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1097756028175354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8150832056999207},{"id":"https://openalex.org/C178718744","wikidata":"https://www.wikidata.org/wiki/Q2350070","display_name":"Voice command device","level":2,"score":0.6944321990013123},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6329526305198669},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5126928091049194},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.49547111988067627},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.4693050682544708},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4581647515296936},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.4460488259792328},{"id":"https://openalex.org/C29794715","wikidata":"https://www.wikidata.org/wiki/Q5362345","display_name":"Smartwatch","level":3,"score":0.4247579872608185},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33903002738952637},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2712784707546234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23802882432937622},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.18118339776992798},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1097756028175354},{"id":"https://openalex.org/C150594956","wikidata":"https://www.wikidata.org/wiki/Q1334829","display_name":"Wearable computer","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/pst52912.2021.9647775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pst52912.2021.9647775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 18th International Conference on Privacy, Security and Trust (PST)","raw_type":"proceedings-article"},{"id":"pmh:oai:ir.library.dc-uoit.ca:10155/1358","is_oa":true,"landing_page_url":"http://hdl.handle.net/10155/1358","pdf_url":"https://ontariotechu.scholaris.ca/bitstreams/c4682750-6e69-4fe4-8d22-75ed86d65330/download","source":{"id":"https://openalex.org/S4306401586","display_name":"e-scholar@UOIT (University of Ontario Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39470171","host_organization_name":"Ontario Tech University","host_organization_lineage":["https://openalex.org/I39470171"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"}],"best_oa_location":{"id":"pmh:oai:ir.library.dc-uoit.ca:10155/1358","is_oa":true,"landing_page_url":"http://hdl.handle.net/10155/1358","pdf_url":"https://ontariotechu.scholaris.ca/bitstreams/c4682750-6e69-4fe4-8d22-75ed86d65330/download","source":{"id":"https://openalex.org/S4306401586","display_name":"e-scholar@UOIT (University of Ontario Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39470171","host_organization_name":"Ontario Tech University","host_organization_lineage":["https://openalex.org/I39470171"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4200004927.pdf","grobid_xml":"https://content.openalex.org/works/W4200004927.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1434018057","https://openalex.org/W1524333225","https://openalex.org/W1673923490","https://openalex.org/W1922655562","https://openalex.org/W2747024632","https://openalex.org/W2811004397","https://openalex.org/W2923292931","https://openalex.org/W2954420970","https://openalex.org/W2962717526","https://openalex.org/W2963058500","https://openalex.org/W2963077926","https://openalex.org/W2964301649","https://openalex.org/W3006816054","https://openalex.org/W3007913795","https://openalex.org/W3042776162","https://openalex.org/W3048605852","https://openalex.org/W3048968121","https://openalex.org/W4287282771","https://openalex.org/W4287329740","https://openalex.org/W4300824008","https://openalex.org/W6628398789","https://openalex.org/W6631362777","https://openalex.org/W6637162671","https://openalex.org/W6640090968","https://openalex.org/W6722479552","https://openalex.org/W6748288002","https://openalex.org/W6760326341","https://openalex.org/W6773727577","https://openalex.org/W6779684038","https://openalex.org/W6780735959","https://openalex.org/W6782061724","https://openalex.org/W6790512348","https://openalex.org/W6791552382"],"related_works":["https://openalex.org/W4235505747","https://openalex.org/W2509150193","https://openalex.org/W2128428210","https://openalex.org/W2399063318","https://openalex.org/W1011691107","https://openalex.org/W2096760943","https://openalex.org/W2953621231","https://openalex.org/W2974139573","https://openalex.org/W2525874696","https://openalex.org/W2001099206"],"abstract_inverted_index":{"Voice":[0],"control":[1,21],"systems":[2,22],"continue":[3],"becoming":[4],"more":[5],"pervasive":[6],"as":[7,30,104],"they":[8,39],"are":[9,40,150],"deployed":[10],"in":[11,107],"mobile":[12],"phones,":[13],"smart":[14,126],"home":[15,127],"devices,":[16],"automobiles,":[17],"etc.":[18],"Commonly,":[19],"voice":[20,43,60,140],"have":[23],"high":[24],"privileges":[25],"on":[26,88],"the":[27,64,76,93,131,147],"device,":[28],"such":[29],"making":[31],"a":[32,155],"call":[33],"or":[34],"placing":[35],"an":[36],"order.":[37],"However,":[38],"vulnerable":[41],"to":[42,48,129,152],"attacks,":[44],"which":[45,57,142],"may":[46],"lead":[47],"serious":[49],"consequences.":[50],"In":[51],"this":[52,136],"paper,":[53],"we":[54,74],"propose":[55],"SegmentPerturb":[56,71],"crafts":[58],"hidden":[59],"commands":[61,141],"via":[62],"inquiring":[63],"target":[65,94],"models.":[66],"The":[67],"general":[68],"idea":[69],"of":[70],"is":[72,103],"that":[73,100,135],"separate":[75],"original":[77],"command":[78],"audio":[79],"into":[80],"multiple":[81],"equal-length":[82],"segments":[83],"and":[84,106,123],"apply":[85],"maximum":[86],"perturbation":[87],"each":[89],"segment":[90],"by":[91,146,154],"probing":[92],"speech":[95,120],"recognition":[96,121],"system.":[97],"We":[98,116],"show":[99],"our":[101],"method":[102],"efficient,":[105],"some":[108],"aspects":[109],"outperforms":[110],"other":[111],"methods":[112],"from":[113],"previous":[114],"works.":[115],"choose":[117],"four":[118],"popular":[119],"APIs":[122],"one":[124],"mainstream":[125],"device":[128],"conduct":[130],"experiments.":[132],"Results":[133],"suggest":[134],"algorithm":[137],"can":[138,143],"generate":[139],"be":[144],"recognized":[145],"machine":[148],"but":[149],"hard":[151],"understand":[153],"human.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
