{"id":"https://openalex.org/W4408345951","doi":"https://doi.org/10.1109/icassp49660.2025.10889621","title":"DiffAttack: Diffusion-based Timbre-reserved Adversarial Attack in Speaker Identification","display_name":"DiffAttack: Diffusion-based Timbre-reserved Adversarial Attack in Speaker Identification","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345951","doi":"https://doi.org/10.1109/icassp49660.2025.10889621"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5100434894","display_name":"Qing Wang","orcid":"https://orcid.org/0000-0003-3439-0644"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qing Wang","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015560758","display_name":"Jixun Yao","orcid":"https://orcid.org/0000-0002-5324-7360"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jixun Yao","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031386845","display_name":"Zhiming Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaokai Sun","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783173","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0001-2388-5935"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science,Xian,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085723847","display_name":"John Hansen","orcid":"https://orcid.org/0000-0003-4989-8117"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John H.L. Hansen","raw_affiliation_strings":["The University of Texas,Center for Robust Speech Systems (CRSS),Dallas,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas,Center for Robust Speech Systems (CRSS),Dallas,USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01644943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.8855999708175659,"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":0.8855999708175659,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.845300018787384,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8384000062942505,"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/timbre","display_name":"Timbre","score":0.7610088586807251},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6953845024108887},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6717391014099121},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6551302671432495},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.620576024055481},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5230223536491394},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.4172735810279846},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.27344077825546265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25364214181900024},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06578868627548218}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.7610088586807251},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6953845024108887},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6717391014099121},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6551302671432495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.620576024055481},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5230223536491394},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.4172735810279846},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.27344077825546265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25364214181900024},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06578868627548218},{"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/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1936725236","https://openalex.org/W2123299109","https://openalex.org/W2165880886","https://openalex.org/W2405506115","https://openalex.org/W2588445447","https://openalex.org/W2726515241","https://openalex.org/W2747874407","https://openalex.org/W2808631503","https://openalex.org/W2890964092","https://openalex.org/W2962747881","https://openalex.org/W2962788625","https://openalex.org/W2963077926","https://openalex.org/W2963542245","https://openalex.org/W2963857521","https://openalex.org/W2972359262","https://openalex.org/W2972394484","https://openalex.org/W2972908178","https://openalex.org/W3007679772","https://openalex.org/W3015811740","https://openalex.org/W3015958938","https://openalex.org/W3024869864","https://openalex.org/W3054852761","https://openalex.org/W3084424094","https://openalex.org/W3095259706","https://openalex.org/W3095570773","https://openalex.org/W3153453329","https://openalex.org/W4250328251","https://openalex.org/W4372260283","https://openalex.org/W4385822891","https://openalex.org/W4385975749","https://openalex.org/W4385993772","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6778823374","https://openalex.org/W6779823529","https://openalex.org/W6783867762","https://openalex.org/W6795261426","https://openalex.org/W6802527329"],"related_works":["https://openalex.org/W2517638034","https://openalex.org/W4366725928","https://openalex.org/W4247725880","https://openalex.org/W2249138175","https://openalex.org/W2120097768","https://openalex.org/W2154141294","https://openalex.org/W2978471304","https://openalex.org/W2100854157","https://openalex.org/W2380891674","https://openalex.org/W2075208738"],"abstract_inverted_index":{"Being":[0],"a":[1,50,61,132],"form":[2],"of":[3,8,15,23,60,110],"biometric":[4],"identification,":[5],"the":[6,9,21,58,82,102,108,127,139,146,153,163,187,192],"security":[7],"speaker":[10,75,148],"identification":[11],"(SID)":[12],"system":[13],"is":[14],"utmost":[16],"importance.":[17],"To":[18],"better":[19],"understand":[20],"robustness":[22],"SID":[24],"systems,":[25],"we":[26,47,89,122],"aim":[27,90],"to":[28,42,67,91,168],"perform":[29],"more":[30],"realistic":[31],"attacks":[32],"in":[33,115],"SID,":[34],"which":[35],"are":[36],"challenging":[37],"for":[38],"humans":[39],"and":[40,119,176],"machines":[41],"detect.":[43],"In":[44],"this":[45],"study,":[46],"propose":[48],"DiffAttack,":[49],"novel":[51],"timbre-reserved":[52],"adversarial":[53,69,79,117,124,135,182],"attack":[54,118,164],"approach,":[55],"that":[56,95,157,180],"exploits":[57],"capability":[59],"diffusion-based":[62,83],"voice":[63,84],"conversion":[64,85],"(DiffVC)":[65],"model":[66],"generate":[68],"fake":[70,93],"audio":[71],"with":[72,145],"distinct":[73],"target":[74,98,147],"attribution.":[76],"By":[77],"introducing":[78,181],"constraints":[80,125,136,183],"into":[81,126],"model\u2019s":[86],"generative":[87],"process,":[88],"craft":[92],"samples":[94],"effectively":[96],"mislead":[97],"models":[99],"while":[100],"preserving":[101],"speaker-wised":[103],"characteristics.":[104],"Specifically,":[105],"inspired":[106],"by":[107,191],"utilization":[109],"randomly":[111],"sampled":[112],"Gaussian":[113],"noise":[114],"conventional":[116],"diffusion":[120,129,141],"processes,":[121],"incorporate":[123],"reverse":[128,140],"process.":[130],"As":[131],"result,":[133],"these":[134],"subtly":[137],"guide":[138],"process":[142],"toward":[143],"aligning":[144],"distribution.":[149],"Our":[150],"experiments":[151],"on":[152],"LibriTTS":[154],"dataset":[155],"indicate":[156],"our":[158],"proposed":[159],"DiffAttack":[160],"significantly":[161],"improves":[162],"success":[165],"rate":[166],"compared":[167],"vanilla":[169],"DiffVC":[170,193],"or":[171],"other":[172],"methods.":[173],"Furthermore,":[174],"objective":[175],"subjective":[177],"evaluations":[178],"demonstrate":[179],"does":[184],"not":[185],"compromise":[186],"speech":[188],"quality":[189],"generated":[190],"model.":[194]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
