{"id":"https://openalex.org/W4406461674","doi":"https://doi.org/10.1109/slt61566.2024.10832168","title":"Adversarial Purification For Speaker Verification By Two-Stage Diffusion Models","display_name":"Adversarial Purification For Speaker Verification By Two-Stage Diffusion Models","publication_year":2024,"publication_date":"2024-12-02","ids":{"openalex":"https://openalex.org/W4406461674","doi":"https://doi.org/10.1109/slt61566.2024.10832168"},"language":"en","primary_location":{"id":"doi:10.1109/slt61566.2024.10832168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832168","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/A5027561341","display_name":"Yibo Bai","orcid":"https://orcid.org/0009-0007-1145-1391"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Yibo Bai","raw_affiliation_strings":["The University of Hong Kong,Dept. of Electrical and Electronic Engineering,Hong Kong,China"],"affiliations":[{"raw_affiliation_string":"The University of Hong Kong,Dept. of Electrical and Electronic Engineering,Hong Kong,China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100450091","display_name":"Xiao-Lei Zhang","orcid":"https://orcid.org/0000-0001-7694-193X"},"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":"Xiao-Lei Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Marine Science and Technology,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106943753","display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0003-2924-946X"},"institutions":[{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":null,"type":"company","lineage":["https://openalex.org/I4387153335"]},{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuelong Li","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI),China Telecom Corp Ltd,Beijing,China"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI),China Telecom Corp Ltd,Beijing,China","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027561341"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23839331,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1158","last_page":"1164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9900000095367432,"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":0.9900000095367432,"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":0.9824000000953674,"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":0.968999981880188,"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/speaker-verification","display_name":"Speaker verification","score":0.8283896446228027},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7780057787895203},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7334997653961182},{"id":"https://openalex.org/keywords/stage","display_name":"Stage (stratigraphy)","score":0.6118499636650085},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5270947217941284},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.45237597823143005},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38177788257598877},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3212141990661621},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.053241610527038574}],"concepts":[{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.8283896446228027},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7780057787895203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7334997653961182},{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.6118499636650085},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5270947217941284},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.45237597823143005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38177788257598877},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3212141990661621},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.053241610527038574},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt61566.2024.10832168","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt61566.2024.10832168","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":[{"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":34,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2962747881","https://openalex.org/W2963542245","https://openalex.org/W2964301649","https://openalex.org/W2971626200","https://openalex.org/W3015811740","https://openalex.org/W3016138785","https://openalex.org/W3024869864","https://openalex.org/W3036167779","https://openalex.org/W3092028330","https://openalex.org/W3095259706","https://openalex.org/W3095498208","https://openalex.org/W3096614974","https://openalex.org/W3097794099","https://openalex.org/W3173081491","https://openalex.org/W3174649707","https://openalex.org/W3204188945","https://openalex.org/W4285340695","https://openalex.org/W4293846201","https://openalex.org/W4320013936","https://openalex.org/W4372340947","https://openalex.org/W4377864733","https://openalex.org/W4385822752","https://openalex.org/W4391640631","https://openalex.org/W4399939422","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6779823529","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6838695150","https://openalex.org/W6853075663"],"related_works":["https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W3141593045","https://openalex.org/W204267554","https://openalex.org/W2134501921","https://openalex.org/W4252590334","https://openalex.org/W2543777506","https://openalex.org/W2407001684","https://openalex.org/W3096066489","https://openalex.org/W3119184205"],"abstract_inverted_index":{"Existing":[0],"research":[1],"has":[2],"demonstrated":[3],"that":[4,96],"speaker":[5,108],"verification":[6],"systems":[7],"can":[8],"be":[9],"vulnerable":[10],"to":[11,23,44,75],"adversarial":[12,17,46,59,67,99,104],"attacks.":[13,27],"In":[14,28],"response,":[15],"numerous":[16],"purification":[18,37,100,120],"techniques":[19],"have":[20],"been":[21],"developed":[22],"defend":[24],"against":[25],"these":[26],"this":[29],"study,":[30],"we":[31],"introduce":[32],"TDP,":[33],"a":[34],"two-stage":[35,41],"diffusion-based":[36],"method,":[38],"which":[39],"employs":[40],"diffusion":[42,113],"models":[43],"purify":[45],"audio":[47],"at":[48,84],"the":[49,58,66,71,80,85,111],"waveform":[50,86],"and":[51,69,92],"latent":[52,62,112],"space":[53],"levels.":[54],"TDP":[55,78,98],"initially":[56],"transforms":[57],"example":[60],"into":[61],"space,":[63],"then":[64],"removes":[65],"perturbation":[68],"converts":[70],"low-dimensional":[72],"vector":[73],"back":[74],"waveform.":[76],"Subsequently,":[77],"purifies":[79],"utterance":[81],"once":[82],"more":[83],"level.":[87],"Experimental":[88],"results":[89],"under":[90],"white-box":[91],"black-box":[93],"attacks":[94],"reveal":[95],"our":[97,116],"method":[101,117],"outperforms":[102],"existing":[103],"defense":[105],"methods":[106],"for":[107],"verification.":[109],"Furthermore,":[110],"model":[114],"in":[115],"significantly":[118],"reduces":[119],"time.":[121]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
