{"id":"https://openalex.org/W4392903328","doi":"https://doi.org/10.1109/icassp48485.2024.10447773","title":"Noise Masking Attacks and Defenses for Pretrained Speech Models","display_name":"Noise Masking Attacks and Defenses for Pretrained Speech Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903328","doi":"https://doi.org/10.1109/icassp48485.2024.10447773"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5054655342","display_name":"Matthew Jagielski","orcid":"https://orcid.org/0000-0002-9749-0696"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Matthew Jagielski","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077162569","display_name":"Om Thakkar","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Om Thakkar","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101419769","display_name":"Lun Wang","orcid":"https://orcid.org/0000-0002-9436-7924"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lun Wang","raw_affiliation_strings":["Google"],"affiliations":[{"raw_affiliation_string":"Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054655342"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.7252,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73036232,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4810","last_page":"4814"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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":0.9980000257492065,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9941999912261963,"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":0.9904999732971191,"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/masking","display_name":"Masking (illustration)","score":0.8324979543685913},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7934274673461914},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7887459397315979},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7336099147796631},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.7113758325576782},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6037447452545166},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33284705877304077}],"concepts":[{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.8324979543685913},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7934274673461914},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7887459397315979},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7336099147796631},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.7113758325576782},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6037447452545166},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33284705877304077},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W108866686","https://openalex.org/W398859631","https://openalex.org/W1494198834","https://openalex.org/W1682403713","https://openalex.org/W2535690855","https://openalex.org/W2615063356","https://openalex.org/W2617258110","https://openalex.org/W3097777922","https://openalex.org/W3177765786","https://openalex.org/W4288057780","https://openalex.org/W4297841588","https://openalex.org/W4297841692","https://openalex.org/W4323066695","https://openalex.org/W4385679821","https://openalex.org/W4400019960","https://openalex.org/W6765055791","https://openalex.org/W6771812881","https://openalex.org/W6787335730","https://openalex.org/W6810463509","https://openalex.org/W6810673746","https://openalex.org/W6839820251","https://openalex.org/W6849141701","https://openalex.org/W6850218400"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W2314871050"],"abstract_inverted_index":{"Speech":[0],"models":[1,37],"are":[2],"often":[3],"trained":[4],"on":[5,105],"sensitive":[6,73],"data":[7],"in":[8],"order":[9],"to":[10,15,85,95,131,144],"improve":[11,132],"model":[12,64,120],"performance,":[13],"leading":[14],"potential":[16],"privacy":[17],"leakage.":[18],"Our":[19,90],"work":[20],"considers":[21],"noise":[22,103],"masking":[23,104],"attacks,":[24],"introduced":[25],"by":[26,38],"Amid":[27],"et":[28],"al.":[29],"[1],":[30],"which":[31,45,108],"attack":[32,86],"automatic":[33],"speech":[34,88],"recognition":[35],"(ASR)":[36],"requesting":[39],"a":[40,55,140],"transcript":[41],"of":[42,135,142],"an":[43,97],"utterance":[44],"is":[46],"partially":[47],"replaced":[48],"with":[49,70],"noise.":[50],"They":[51],"show":[52,129],"that":[53],"when":[54],"record":[56,69],"has":[57],"been":[58],"seen":[59,123],"at":[60,125],"training":[61],"time,":[62],"the":[63,67,93,115,119,133],"will":[65],"transcribe":[66],"noisy":[68],"its":[71],"memorized":[72],"transcript.":[74],"In":[75],"our":[76,145],"work,":[77],"we":[78,109],"extend":[79],"these":[80,136],"attacks":[81,137],"beyond":[82],"ASR":[83,98],"models,":[84],"pretrained":[87],"encoders.":[89],"method":[91],"fine-tunes":[92],"encoder":[94],"produce":[96],"model,":[99,107],"and":[100,138],"then":[101],"performs":[102],"this":[106],"find":[110],"recovers":[111],"private":[112],"information":[113],"from":[114],"pretraining":[116,126],"data,":[117],"despite":[118],"never":[121],"having":[122],"transcripts":[124],"time!":[127],"We":[128],"how":[130],"precision":[134],"investigate":[139],"number":[141],"countermeasures":[143],"attacks.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}