{"id":"https://openalex.org/W3095413397","doi":"https://doi.org/10.1109/icassp39728.2021.9414843","title":"Adversarial Defense for Deep Speaker Recognition Using Hybrid Adversarial Training","display_name":"Adversarial Defense for Deep Speaker Recognition Using Hybrid Adversarial Training","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3095413397","doi":"https://doi.org/10.1109/icassp39728.2021.9414843","mag":"3095413397"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.16038","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027587001","display_name":"Monisankha Pal","orcid":"https://orcid.org/0000-0002-0788-4158"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Monisankha Pal","raw_affiliation_strings":["University of Southern California (USC),Signal Analysis and Interpretation Laboratory,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California (USC),Signal Analysis and Interpretation Laboratory,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067289130","display_name":"Arindam Jati","orcid":"https://orcid.org/0000-0002-9498-8536"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arindam Jati","raw_affiliation_strings":["University of Southern California (USC),Signal Analysis and Interpretation Laboratory,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California (USC),Signal Analysis and Interpretation Laboratory,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086205666","display_name":"Raghuveer Peri","orcid":"https://orcid.org/0000-0002-1010-065X"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raghuveer Peri","raw_affiliation_strings":["University of Southern California (USC),Signal Analysis and Interpretation Laboratory,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California (USC),Signal Analysis and Interpretation Laboratory,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028115568","display_name":"Chin-Cheng Hsu","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chin-Cheng Hsu","raw_affiliation_strings":["University of Southern California (USC),Signal Analysis and Interpretation Laboratory,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California (USC),Signal Analysis and Interpretation Laboratory,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028776484","display_name":"Wael AbdAlmageed","orcid":"https://orcid.org/0000-0002-8320-8530"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wael AbdAlmageed","raw_affiliation_strings":["USC Information Sciences Institute,Marina del Rey,USA","USC Information Sciences Institute, Marina Del Rey, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"USC Information Sciences Institute,Marina del Rey,USA","institution_ids":[]},{"raw_affiliation_string":"USC Information Sciences Institute, Marina Del Rey, USA#TAB#","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern California (USC),Signal Analysis and Interpretation Laboratory,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California (USC),Signal Analysis and Interpretation Laboratory,USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2931,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.4759964,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"6164","last_page":"6168"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9995999932289124,"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":0.9995999932289124,"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/T11242","display_name":"Nuclear Materials and Properties","score":0.9434999823570251,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9193000197410583,"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/adversarial-system","display_name":"Adversarial system","score":0.9420396089553833},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7423292398452759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6011191606521606},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5904464721679688},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.584833025932312},{"id":"https://openalex.org/keywords/adversary","display_name":"Adversary","score":0.5767126083374023},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5625280737876892},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.519483208656311},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4663013517856598},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4518139958381653},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.443258672952652},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.42077043652534485},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40555381774902344},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3908815383911133},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36991173028945923},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.21044856309890747}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9420396089553833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7423292398452759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6011191606521606},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5904464721679688},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.584833025932312},{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.5767126083374023},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5625280737876892},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.519483208656311},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4663013517856598},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4518139958381653},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.443258672952652},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.42077043652534485},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40555381774902344},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3908815383911133},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36991173028945923},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.21044856309890747},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2010.16038","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.16038","pdf_url":"https://arxiv.org/pdf/2010.16038","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3095413397","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2010.16038","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2010.16038","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.16038","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/jstb-vb51","is_oa":true,"landing_page_url":"https://doi.org/10.17023/jstb-vb51","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.16038","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.16038","pdf_url":"https://arxiv.org/pdf/2010.16038","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3095413397.pdf","grobid_xml":"https://content.openalex.org/works/W3095413397.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2077740952","https://openalex.org/W2154278880","https://openalex.org/W2158131535","https://openalex.org/W2523246573","https://openalex.org/W2640329709","https://openalex.org/W2787708942","https://openalex.org/W2885407017","https://openalex.org/W2913848079","https://openalex.org/W2923292931","https://openalex.org/W2952730822","https://openalex.org/W2962747881","https://openalex.org/W2963058500","https://openalex.org/W2963178695","https://openalex.org/W2963207607","https://openalex.org/W2963389226","https://openalex.org/W2963857521","https://openalex.org/W2964153729","https://openalex.org/W2964301649","https://openalex.org/W2970451906","https://openalex.org/W2972533226","https://openalex.org/W2972908178","https://openalex.org/W2985489290","https://openalex.org/W2986674980","https://openalex.org/W3009153202","https://openalex.org/W3013520104","https://openalex.org/W3015811740","https://openalex.org/W3016138785","https://openalex.org/W3084424094","https://openalex.org/W3131867595","https://openalex.org/W6629717138","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6682962330","https://openalex.org/W6727249380","https://openalex.org/W6729756640","https://openalex.org/W6739868092","https://openalex.org/W6748475379","https://openalex.org/W6758975236","https://openalex.org/W6760326341","https://openalex.org/W6766725774","https://openalex.org/W6769842499","https://openalex.org/W6790918573"],"related_works":["https://openalex.org/W3162760878","https://openalex.org/W2901368553","https://openalex.org/W3162158711","https://openalex.org/W3026494492","https://openalex.org/W3084424094","https://openalex.org/W3015958938","https://openalex.org/W2984968650","https://openalex.org/W3081785824","https://openalex.org/W3138740729","https://openalex.org/W3012093053","https://openalex.org/W2954420970","https://openalex.org/W3128911095","https://openalex.org/W3162258435","https://openalex.org/W2889910486","https://openalex.org/W3011838870","https://openalex.org/W2900161882","https://openalex.org/W3091539257","https://openalex.org/W2962909949","https://openalex.org/W2965116050","https://openalex.org/W3015737406"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"network":[2],"based":[3,52],"speaker":[4,32,72,135],"recognition":[5,33,73,136],"systems":[6,34],"can":[7],"easily":[8],"be":[9],"deceived":[10],"by":[11,79,165],"an":[12],"adversary":[13],"using":[14,109],"minuscule":[15],"imperceptible":[16],"perturbations":[17,100,119],"to":[18,30,62,86,95,116,126],"the":[19,31,128,131,139,144],"input":[20],"speech":[21,37],"samples.":[22],"These":[23],"adversarial":[24,56,68,102,118,124,152,163],"attacks":[25,69,175],"pose":[26],"serious":[27],"security":[28],"threats":[29],"that":[35,74],"use":[36,76],"biometric.":[38],"To":[39],"address":[40],"this":[41,44],"concern,":[42],"in":[43,70],"work,":[45],"we":[46,84,105],"propose":[47,85],"a":[48,54],"new":[49],"defense":[50],"mechanism":[51],"on":[53,65,138,181],"hybrid":[55],"training":[57,125,153],"(HAT)":[58],"setup.":[59],"In":[60],"contrast":[61],"existing":[63],"works":[64],"countermeasures":[66],"against":[67],"deep":[71],"only":[75,156],"class-boundary":[77],"information":[78,89],"supervised":[80,91],"cross-entropy":[81],"(CE)":[82],"loss,":[83],"exploit":[87],"additional":[88],"from":[90],"and":[92,98,113,120,142,168,172],"unsupervised":[93],"cues":[94],"craft":[96],"diverse":[97],"stronger":[99],"for":[101,123,170],"training.":[103],"Specifically,":[104],"employ":[106],"multi-task":[107],"objectives":[108],"CE,":[110],"feature-scattering":[111],"(FS),":[112],"margin":[114],"losses":[115],"create":[117],"include":[121],"them":[122],"enhance":[127],"robustness":[129],"of":[130],"model.":[132],"We":[133],"conduct":[134],"experiments":[137],"Librispeech":[140],"dataset,":[141],"compare":[143],"performance":[145],"with":[146],"state-of-the-art":[147],"projected":[148],"gradient":[149],"descent":[150],"(PGD)-based":[151],"which":[154],"employs":[155],"CE":[157],"objective.":[158],"The":[159],"proposed":[160],"HAT":[161],"improves":[162],"accuracy":[164,180],"absolute":[166],"3.29%":[167],"3.18%":[169],"PGD":[171],"Carlini-Wagner":[173],"(CW)":[174],"respectively,":[176],"while":[177],"retaining":[178],"high":[179],"benign":[182],"examples.":[183]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}