{"id":"https://openalex.org/W4408354770","doi":"https://doi.org/10.1109/icassp49660.2025.10888789","title":"FreqSense: Universal and Low-Latency Adversarial Example Detection for Speaker Recognition with Interpretability in Frequency Domain","display_name":"FreqSense: Universal and Low-Latency Adversarial Example Detection for Speaker Recognition with Interpretability in Frequency Domain","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354770","doi":"https://doi.org/10.1109/icassp49660.2025.10888789"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888789","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/A5018218023","display_name":"Yihuan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yihuan Huang","raw_affiliation_strings":["Ministry of Education,Key Laboratory of Aerospace Information Security and Trusted Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Education,Key Laboratory of Aerospace Information Security and Trusted Computing","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100699371","display_name":"Yuanzhe Li","orcid":"https://orcid.org/0000-0001-7530-8286"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanzhe Li","raw_affiliation_strings":["Wuhan University,School of Cyber Science and Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,School of Cyber Science and Engineering","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101499462","display_name":"Yanzhen Ren","orcid":"https://orcid.org/0000-0003-0799-5082"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanzhen Ren","raw_affiliation_strings":["Ministry of Education,Key Laboratory of Aerospace Information Security and Trusted Computing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ministry of Education,Key Laboratory of Aerospace Information Security and Trusted Computing","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041664453","display_name":"Weiping Tu","orcid":"https://orcid.org/0000-0002-6933-3298"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiping Tu","raw_affiliation_strings":["Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102859655","display_name":"Yuhong Yang","orcid":"https://orcid.org/0000-0003-3001-7957"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhong Yang","raw_affiliation_strings":["Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University,National Engineering Research Center for Multimedia Software, School of Computer Science","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.01709552,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9717000126838684,"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":0.9717000126838684,"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/T12560","display_name":"Nuclear Engineering Thermal-Hydraulics","score":0.9133999943733215,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9031000137329102,"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/interpretability","display_name":"Interpretability","score":0.9285873174667358},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7592098712921143},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7577661871910095},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5953246355056763},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.5609965920448303},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5022430419921875},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4866796135902405},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.46139025688171387},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44103318452835083},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42410892248153687},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.358495831489563},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12194347381591797},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.097165048122406},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.06858751177787781}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9285873174667358},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7592098712921143},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7577661871910095},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5953246355056763},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.5609965920448303},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5022430419921875},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4866796135902405},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.46139025688171387},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44103318452835083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42410892248153687},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.358495831489563},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12194347381591797},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.097165048122406},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.06858751177787781},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888789","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":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1996443744","https://openalex.org/W2153002160","https://openalex.org/W2243397390","https://openalex.org/W2939099741","https://openalex.org/W2963542245","https://openalex.org/W2963857521","https://openalex.org/W2963925437","https://openalex.org/W2972908178","https://openalex.org/W2973032144","https://openalex.org/W3016138785","https://openalex.org/W3091896612","https://openalex.org/W3153453329","https://openalex.org/W3156272176","https://openalex.org/W3160636055","https://openalex.org/W3162096084","https://openalex.org/W3204188945","https://openalex.org/W3207651366","https://openalex.org/W4225297350","https://openalex.org/W4297841898","https://openalex.org/W4312458120","https://openalex.org/W4388562958","https://openalex.org/W4390421837","https://openalex.org/W4392904223","https://openalex.org/W6640425456","https://openalex.org/W6703049675","https://openalex.org/W6727697161","https://openalex.org/W6739868092","https://openalex.org/W6754602573","https://openalex.org/W6780218876","https://openalex.org/W6791552382","https://openalex.org/W6852816340"],"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":{"Speaker":[0],"recognition":[1],"(SR)":[2],"systems":[3,18],"are":[4,19,90],"particularly":[5],"vulnerable":[6],"to":[7,134],"adversarial":[8],"example":[9],"(AE)":[10],"attacks.":[11],"To":[12,25],"mitigate":[13],"these":[14,103],"attacks,":[15,163],"AE":[16,46,60,79,110,137,162],"detection":[17,31,47,70,149,167],"typically":[20,80],"integrated":[21],"into":[22],"SR":[23],"systems.":[24],"overcome":[26],"the":[27,99],"limitations":[28],"of":[29,58,75,151,169,174],"low":[30,63],"accuracy,":[32],"poor":[33],"generalization,":[34],"and":[35,65,111,128,138],"high":[36],"latency":[37,173],"in":[38,68,85,102],"existing":[39],"schemes,":[40],"this":[41],"paper":[42],"proposes":[43],"FreqSense,":[44],"an":[45,147],"scheme":[48],"based":[49],"on":[50],"frequency":[51,87,104,116],"distribution":[52,117],"features.":[53],"FreqSense":[54,76,114,145,164],"detects":[55],"a":[56,125,130,166,172],"variety":[57],"unknown":[59,161],"attacks":[61],"with":[62,92,124,171],"latency,":[64],"provides":[66],"interpretability":[67],"its":[69],"process.":[71],"The":[72],"basic":[73],"idea":[74],"is":[77],"that":[78,89,144],"introduce":[81],"carefully":[82],"designed":[83],"noise":[84],"specific":[86],"bands":[88,105],"associated":[91],"highly":[93],"distinctive":[94],"speaker":[95],"identities.":[96],"Therefore,":[97],"leveraging":[98],"distributional":[100],"variations":[101],"can":[106],"effectively":[107],"distinguish":[108,135],"between":[109,136],"benign":[112,139],"audio.":[113,140],"models":[115],"features":[118],"by":[119,157],"integrating":[120],"time-frequency":[121],"transformation":[122],"technology":[123],"self-attention":[126],"mechanism":[127],"employs":[129],"neural":[131],"network-based":[132],"classifier":[133],"Experimental":[141],"results":[142],"show":[143],"achieves":[146,165],"overall":[148],"accuracy":[150,168],"99.2%,":[152],"surpassing":[153],"state-of-the-art":[154],"(SOTA)":[155],"schemes":[156],"27.2%.":[158],"When":[159],"confronting":[160],"98.3%":[170],"just":[175],"0.0014":[176],"seconds.":[177]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}