{"id":"https://openalex.org/W4406461986","doi":"https://doi.org/10.1109/slt61566.2024.10832273","title":"Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Multi-Task Automatic Speech Recognition Models","display_name":"Controlling Whisper: Universal Acoustic Adversarial Attacks to Control Multi-Task Automatic Speech Recognition Models","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461986","doi":"https://doi.org/10.1109/slt61566.2024.10832273"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","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/A5024132945","display_name":"Vyas Raina","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Vyas Raina","raw_affiliation_strings":["University of Cambridge"],"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Gales","raw_affiliation_strings":["University of Cambridge"],"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5024132945"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23857973,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"208","last_page":"215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","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/T11689","display_name":"Adversarial Robustness in Machine Learning","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/T10951","display_name":"Cryptographic Implementations and Security","score":0.9386000037193298,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.917900025844574,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7906204462051392},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7840703725814819},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6846415400505066},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6397527456283569},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5166400074958801},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4605919122695923},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3603626489639282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3088911771774292},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10446900129318237}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7906204462051392},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7840703725814819},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6846415400505066},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6397527456283569},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5166400074958801},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4605919122695923},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3603626489639282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3088911771774292},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10446900129318237},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2767951891","https://openalex.org/W2782403400","https://openalex.org/W2885407017","https://openalex.org/W2923292931","https://openalex.org/W2962717526","https://openalex.org/W2963058500","https://openalex.org/W2963077926","https://openalex.org/W2963161670","https://openalex.org/W2964253222","https://openalex.org/W2964301649","https://openalex.org/W2972706975","https://openalex.org/W2973057252","https://openalex.org/W2973252307","https://openalex.org/W3091896612","https://openalex.org/W3097642048","https://openalex.org/W3105214104","https://openalex.org/W3105332166","https://openalex.org/W3109668151","https://openalex.org/W3129501265","https://openalex.org/W3167676691","https://openalex.org/W3197946353","https://openalex.org/W3207651366","https://openalex.org/W4311000453","https://openalex.org/W4319862635","https://openalex.org/W4375958083","https://openalex.org/W4385245566","https://openalex.org/W4385822685","https://openalex.org/W4391021666","https://openalex.org/W4391968469","https://openalex.org/W4392902623","https://openalex.org/W4392903956","https://openalex.org/W4392931626","https://openalex.org/W4404782822","https://openalex.org/W6722479552","https://openalex.org/W6739868092","https://openalex.org/W6745795967","https://openalex.org/W6746882984","https://openalex.org/W6748288002","https://openalex.org/W6751746874","https://openalex.org/W6759133231","https://openalex.org/W6760326341","https://openalex.org/W6782072790","https://openalex.org/W6786041164","https://openalex.org/W6838929754","https://openalex.org/W6847363464","https://openalex.org/W6852326057","https://openalex.org/W6857054612"],"related_works":["https://openalex.org/W2044408773","https://openalex.org/W2130717063","https://openalex.org/W4383605217","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W2533508831","https://openalex.org/W1599055764","https://openalex.org/W48790062","https://openalex.org/W2131711534"],"abstract_inverted_index":{"Speech":[0],"enabled":[1,189],"foundation":[2,150,190],"models,":[3],"either":[4],"in":[5],"the":[6,26,50,63,70,87,100,108,111,116,144,199],"form":[7,182,203],"of":[8,25,29,65,110,147,183,201,204],"flexible":[9],"speech":[10,41,57,60,140,167,174,188],"recognition":[11,42],"based":[12],"systems":[13,88],"or":[14],"audio-prompted":[15,66],"large":[16],"language":[17],"models":[18,31,191],"(LLMs),":[19],"are":[20],"becoming":[21],"increasingly":[22],"popular.":[23],"One":[24],"interesting":[27],"aspects":[28],"these":[30],"is":[32,69,104,127],"their":[33],"ability":[34],"to":[35,92,99,106,129,137,142,161,164,172,194,198],"perform":[36,55,166,173],"tasks":[37],"other":[38],"than":[39],"automatic":[40],"(ASR)":[43],"using":[44],"an":[45,148],"appropriate":[46],"prompt.":[47],"For":[48],"example,":[49],"OpenAI":[51],"Whisper":[52,163],"model":[53,101],"can":[54,89],"both":[56],"transcription":[58],"and":[59],"translation.":[61],"With":[62],"development":[64],"LLMs":[67],"there":[68],"potential":[71],"for":[72],"even":[73],"greater":[74,85],"control":[75,162],"options.":[76],"In":[77],"this":[78,84,121,177,202],"work":[79,178],"we":[80,123,153],"demonstrate":[81,124],"that":[82,125,192],"with":[83],"flexibility":[86],"be":[90,195],"susceptible":[91],"model-control":[93],"adversarial":[94,134,158,184],"attacks.":[95],"Without":[96],"any":[97,138],"access":[98],"prompt":[102,145],"it":[103,126],"possible":[105,128],"modify":[107],"behaviour":[109],"system":[112],"by":[113],"appropriately":[114],"changing":[115],"audio":[117],"input.":[118],"To":[119],"illustrate":[120],"risk,":[122],"prepend":[130],"a":[131,156,180],"short":[132],"universal":[133,157],"acoustic":[135,159],"segment":[136,160],"input":[139],"signal":[141],"override":[143],"setting":[146],"ASR":[149],"model.":[151,205],"Specifically,":[152],"successfully":[154],"use":[155],"always":[165],"translation,":[168],"despite":[169],"being":[170],"set":[171],"transcription.":[175],"Overall,":[176],"demonstrates":[179],"new":[181],"attack":[185],"on":[186],"multi-tasking":[187],"needs":[193],"considered":[196],"prior":[197],"deployment":[200]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}