{"id":"https://openalex.org/W4408324485","doi":"https://doi.org/10.1109/globecom52923.2024.10901725","title":"BadTTS: Identifying Vulnerabilities in Neural Text-to-Speech Models","display_name":"BadTTS: Identifying Vulnerabilities in Neural Text-to-Speech Models","publication_year":2024,"publication_date":"2024-12-08","ids":{"openalex":"https://openalex.org/W4408324485","doi":"https://doi.org/10.1109/globecom52923.2024.10901725"},"language":"en","primary_location":{"id":"doi:10.1109/globecom52923.2024.10901725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom52923.2024.10901725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2024 - 2024 IEEE Global Communications Conference","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/A5100421978","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0001-9418-0863"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Computer Science and Engineering","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325327","display_name":"Hongwei Li","orcid":"https://orcid.org/0000-0001-9461-4668"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwei Li","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Computer Science and Engineering","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038280308","display_name":"Wenbo Jiang","orcid":"https://orcid.org/0000-0001-6138-3082"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Jiang","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Computer Science and Engineering","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075371310","display_name":"Ran Zhang","orcid":"https://orcid.org/0000-0002-3808-281X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China,School of Computer Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China,School of Computer Science and Engineering","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101721206","display_name":"Jiaming He","orcid":"https://orcid.org/0009-0007-9529-7327"},"institutions":[{"id":"https://openalex.org/I31595395","display_name":"Chengdu University of Technology","ror":"https://ror.org/05pejbw21","country_code":"CN","type":"education","lineage":["https://openalex.org/I31595395"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaming He","raw_affiliation_strings":["Chengdu University of Technology,College of Computer Science and Cyber Security (Oxford Brookes College),China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chengdu University of Technology,College of Computer Science and Cyber Security (Oxford Brookes College),China","institution_ids":["https://openalex.org/I31595395"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3146","last_page":"3151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9289000034332275,"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":0.9289000034332275,"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":0.8125668168067932},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46400776505470276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4502432346343994},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4478783905506134},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4245457351207733}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8125668168067932},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46400776505470276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4502432346343994},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4478783905506134},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4245457351207733}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globecom52923.2024.10901725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom52923.2024.10901725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2024 - 2024 IEEE Global Communications Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.47999998927116394}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336736","display_name":"Chengdu Science and Technology Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2090755665","https://openalex.org/W2164107060","https://openalex.org/W2941048526","https://openalex.org/W2964243274","https://openalex.org/W2983633287","https://openalex.org/W3013045184","https://openalex.org/W3095883095","https://openalex.org/W4386083011","https://openalex.org/W4387967988","https://openalex.org/W4396982204","https://openalex.org/W6691808304","https://openalex.org/W6743581629","https://openalex.org/W6755257315","https://openalex.org/W6774779085","https://openalex.org/W6777694618","https://openalex.org/W6847363464","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"With":[0],"the":[1,44,50,56,60,71,91,112,165,171,180,228,238],"widespread":[2],"use":[3],"of":[4,39,103,185,193,230,233,241],"deep":[5,32],"learning":[6],"systems":[7,20],"in":[8,80,131,174],"many":[9],"applications,":[10],"adversaries":[11],"have":[12,26],"strong":[13],"incentives":[14],"to":[15,58,90,135,226],"perform":[16,197],"attacks":[17,30,79,93,105],"against":[18,116,249],"these":[19],"for":[21,189,246],"their":[22],"adversarial":[23],"purposes.":[24],"Reports":[25],"indicated":[27],"that":[28,126,209],"backdoor":[29,63,78,92,104,114,123,172,250],"on":[31,77,94,106,164,200],"neural":[33],"networks":[34],"represent":[35],"a":[36,66,100,121,153,175,190,218],"novel":[37],"form":[38],"threat.":[40],"In":[41],"this":[42],"attack,":[43],"adversary":[45,181],"will":[46],"inject":[47],"backdoors":[48,151,210],"into":[49,152,214],"benign":[51],"model":[52,57,155,186],"and":[53,82,109,143,160,203],"then":[54],"mislead":[55],"classify":[59],"input":[61,129],"containing":[62],"triggers":[64],"as":[65,235,237],"target":[67],"label":[68],"specified":[69],"by":[70],"adversary.":[72],"Existing":[73],"research":[74],"mainly":[75],"focuses":[76],"image":[81],"text":[83],"models,":[84,118,207,242],"little":[85,162],"attention":[86],"has":[87,161,182],"been":[88],"paid":[89],"text-to-speech":[95,107],"(TTS)":[96],"models.":[97],"We":[98,169,196],"conduct":[99,224],"systematic":[101],"investigation":[102],"models":[108,216],"propose":[110],"BadTTS,":[111],"first":[113],"attack":[115,124,173],"TTS":[117,154,206,215],"which":[119,243],"is":[120,157],"general":[122],"framework":[125],"tampers":[127],"with":[128],"texts":[130],"three":[132,201],"semantic":[133],"levels":[134],"generate":[136],"malicious":[137],"output":[138],"speech,":[139],"including":[140],"Char-Backdoor,":[141],"Word-Backdoor,":[142],"Sentence-Backdoor.":[144],"Our":[145],"method":[146],"not":[147],"only":[148],"efficiently":[149],"injects":[150],"but":[156],"also":[158],"stealthy":[159],"impact":[163,229],"synthesized":[166],"speech":[167],"quality.":[168],"implement":[170],"black-box":[176],"fine-tuning":[177,220],"setting,":[178],"where":[179],"no":[183],"knowledge":[184],"architectures":[187],"except":[188],"small":[191],"amount":[192],"training":[194],"data.":[195],"empirical":[198],"experiments":[199,225],"representative":[202],"widely":[204],"studied":[205],"indicating":[208],"can":[211],"be":[212],"injected":[213],"within":[217],"few":[219],"steps.":[221],"Additionally,":[222],"we":[223],"explore":[227],"different":[231],"types":[232],"triggers,":[234],"well":[236],"intermediate":[239],"outputs":[240],"provide":[244],"insights":[245],"potential":[247],"defenses":[248],"attacks.":[251]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}