{"id":"https://openalex.org/W4200444305","doi":"https://doi.org/10.1145/3485832.3485892","title":"CommanderGabble: A Universal Attack Against ASR Systems Leveraging Fast Speech","display_name":"CommanderGabble: A Universal Attack Against ASR Systems Leveraging Fast Speech","publication_year":2021,"publication_date":"2021-12-06","ids":{"openalex":"https://openalex.org/W4200444305","doi":"https://doi.org/10.1145/3485832.3485892"},"language":"en","primary_location":{"id":"doi:10.1145/3485832.3485892","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485832.3485892","pdf_url":null,"source":{"id":"https://openalex.org/S4306417673","display_name":"Annual Computer Security Applications Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annual Computer Security Applications Conference","raw_type":"proceedings-article"},"type":"article","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/A5066964790","display_name":"Zhaohe Zhang","orcid":"https://orcid.org/0000-0002-6542-0319"},"institutions":[{"id":"https://openalex.org/I8692664","display_name":"University of Oklahoma","ror":"https://ror.org/02aqsxs83","country_code":"US","type":"education","lineage":["https://openalex.org/I8692664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhaohe (John) Zhang","raw_affiliation_strings":["University of Oklahoma, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oklahoma, USA","institution_ids":["https://openalex.org/I8692664"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029127060","display_name":"Edwin Yang","orcid":"https://orcid.org/0000-0002-1794-5014"},"institutions":[{"id":"https://openalex.org/I8692664","display_name":"University of Oklahoma","ror":"https://ror.org/02aqsxs83","country_code":"US","type":"education","lineage":["https://openalex.org/I8692664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edwin Yang","raw_affiliation_strings":["University of Oklahoma, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oklahoma, USA","institution_ids":["https://openalex.org/I8692664"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091078914","display_name":"Song Fang","orcid":"https://orcid.org/0000-0002-2354-3310"},"institutions":[{"id":"https://openalex.org/I8692664","display_name":"University of Oklahoma","ror":"https://ror.org/02aqsxs83","country_code":"US","type":"education","lineage":["https://openalex.org/I8692664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Song Fang","raw_affiliation_strings":["University of Oklahoma, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oklahoma, United States of America","institution_ids":["https://openalex.org/I8692664"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5073,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67005545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"720","last_page":"731"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9930999875068665,"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":0.9930999875068665,"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":0.8386033773422241},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5684972405433655},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5677175521850586},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5305861234664917},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.48479098081588745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.272446870803833},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.09428480267524719}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8386033773422241},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5684972405433655},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5677175521850586},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5305861234664917},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.48479098081588745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.272446870803833},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.09428480267524719},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3485832.3485892","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3485832.3485892","pdf_url":null,"source":{"id":"https://openalex.org/S4306417673","display_name":"Annual Computer Security Applications Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Annual Computer Security Applications Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5899999737739563}],"awards":[{"id":"https://openalex.org/G522434985","display_name":null,"funder_award_id":"1948547","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W57926798","https://openalex.org/W95608104","https://openalex.org/W1499360075","https://openalex.org/W1637570796","https://openalex.org/W2049333779","https://openalex.org/W2111056602","https://openalex.org/W2151534206","https://openalex.org/W2155569120","https://openalex.org/W2168961642","https://openalex.org/W2766001563","https://openalex.org/W2801659857","https://openalex.org/W2921394285","https://openalex.org/W2933426098","https://openalex.org/W2947292651","https://openalex.org/W2952654825","https://openalex.org/W2963058500","https://openalex.org/W2963077926","https://openalex.org/W2973057252","https://openalex.org/W3006816054","https://openalex.org/W3007913795","https://openalex.org/W3109668151","https://openalex.org/W4234508879","https://openalex.org/W4237333442","https://openalex.org/W4238579241","https://openalex.org/W4297987871","https://openalex.org/W4300824008","https://openalex.org/W6631362777","https://openalex.org/W7048551012"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492"],"abstract_inverted_index":{"Automatic":[0],"Speech":[1],"Recognition":[2],"(ASR)":[3],"systems":[4,25,92],"are":[5,26,187],"widely":[6],"used":[7],"in":[8,195],"various":[9],"online":[10],"transcription":[11],"services":[12],"and":[13,75,90,97,142,144,182],"personal":[14],"digital":[15],"assistants.":[16],"Emerging":[17],"lines":[18],"of":[19,54,116,148,174],"research":[20],"have":[21],"demonstrated":[22],"that":[23,34,163,183],"ASR":[24,91,157],"vulnerable":[27],"to":[28,64,84,103,125,150],"hidden":[29,105,128],"voice":[30,86,106,119,177],"commands,":[31],"i.e.,":[32],"audio":[33],"can":[35,100,122,167],"be":[36,101,123],"recognized":[37],"by":[38,42,110],"ASRs":[39,121],"but":[40],"not":[41],"humans.":[43],"Such":[44],"attacks,":[45],"however,":[46],"often":[47,93],"either":[48],"highly":[49],"depend":[50],"on":[51],"white-box":[52],"knowledge":[53],"a":[55,72,117,127,146],"specific":[56],"machine":[57],"learning":[58],"model":[59],"or":[60],"require":[61],"special":[62],"hardware":[63],"construct":[65],"the":[66,113,131,137,164,184],"adversarial":[67,180],"audio.":[68],"This":[69],"paper":[70],"proposes":[71],"new":[73],"model-agnostic":[74],"easily-constructed":[76],"attack,":[77],"called":[78],"CommanderGabble,":[79],"which":[80],"uses":[81],"fast":[82,95],"speech":[83],"camouflage":[85],"commands.":[87],"Both":[88],"humans":[89],"misinterpret":[94],"speech,":[96],"such":[98],"misinterpretation":[99],"exploited":[102],"launch":[104],"command":[107],"attacks.":[108],"Specifically,":[109],"carefully":[111],"manipulating":[112],"phonetic":[114],"structure":[115],"target":[118],"command,":[120],"caused":[124],"derive":[126],"meaning":[129],"from":[130],"manipulated,":[132],"high-speed":[133],"version.":[134],"We":[135],"implement":[136],"discovered":[138],"attacks":[139,166,186],"both":[140],"over-the-wire":[141,165],"over-the-air,":[143],"conduct":[145],"suite":[147],"experiments":[149],"demonstrate":[151],"their":[152],"efficacy":[153],"against":[154],"7":[155],"practical":[156],"systems.":[158],"Our":[159],"experimental":[160],"results":[161],"show":[162],"disguise":[168],"as":[169,171],"many":[170],"96":[172],"out":[173],"100":[175],"tested":[176],"commands":[178,194],"into":[179],"ones,":[181],"over-the-air":[185],"consistently":[188],"successful":[189],"for":[190],"all":[191],"18":[192],"chosen":[193],"multiple":[196],"real-world":[197],"scenarios.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}