{"id":"https://openalex.org/W4405014384","doi":"https://doi.org/10.1145/3636534.3690692","title":"WavePurifier: Purifying Audio Adversarial Examples via Hierarchical Diffusion Models","display_name":"WavePurifier: Purifying Audio Adversarial Examples via Hierarchical Diffusion Models","publication_year":2024,"publication_date":"2024-12-04","ids":{"openalex":"https://openalex.org/W4405014384","doi":"https://doi.org/10.1145/3636534.3690692"},"language":"en","primary_location":{"id":"doi:10.1145/3636534.3690692","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3636534.3690692","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3636534.3690692","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th Annual International Conference on Mobile Computing and Networking","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3636534.3690692","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035545617","display_name":"Hanqing Guo","orcid":"https://orcid.org/0000-0003-3779-4679"},"institutions":[{"id":"https://openalex.org/I117965899","display_name":"University of Hawai\u02bbi at M\u0101noa","ror":"https://ror.org/01wspgy28","country_code":"US","type":"education","lineage":["https://openalex.org/I117965899"]},{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hanqing Guo","raw_affiliation_strings":["Michigan State University, East Lansing, US","University of Hawaii at Manoa, Honolulu, USA"],"raw_orcid":"https://orcid.org/0000-0003-3779-4679","affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, US","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"University of Hawaii at Manoa, Honolulu, USA","institution_ids":["https://openalex.org/I117965899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083819169","display_name":"Guangjing Wang","orcid":"https://orcid.org/0000-0002-9353-9042"},"institutions":[{"id":"https://openalex.org/I2613432","display_name":"University of South Florida","ror":"https://ror.org/032db5x82","country_code":"US","type":"education","lineage":["https://openalex.org/I2613432"]},{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guangjing Wang","raw_affiliation_strings":["Michigan State University, East Lansing, US","University of South Florida, Tampa, USA"],"raw_orcid":"https://orcid.org/0000-0002-9353-9042","affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, US","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"University of South Florida, Tampa, USA","institution_ids":["https://openalex.org/I2613432"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076545839","display_name":"Bocheng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bocheng Chen","raw_affiliation_strings":["Michigan State University, East Lansing, USA"],"raw_orcid":"https://orcid.org/0009-0001-0471-7063","affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039317227","display_name":"Y. Wang","orcid":"https://orcid.org/0009-0008-2062-9013"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanda Wang","raw_affiliation_strings":["Michigan State University, East Lansing, US"],"raw_orcid":"https://orcid.org/0009-0008-2062-9013","affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, US","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026121963","display_name":"Xiao Zhang","orcid":"https://orcid.org/0000-0002-7392-3477"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiao Zhang","raw_affiliation_strings":["Duke University, Durham, USA"],"raw_orcid":"https://orcid.org/0000-0002-7392-3477","affiliations":[{"raw_affiliation_string":"Duke University, Durham, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070178604","display_name":"Xun Chen","orcid":"https://orcid.org/0000-0001-5208-7775"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xun Chen","raw_affiliation_strings":["Samsung Research America, Mountain View, US"],"raw_orcid":"https://orcid.org/0000-0001-5208-7775","affiliations":[{"raw_affiliation_string":"Samsung Research America, Mountain View, US","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042277127","display_name":"Qiben Yan","orcid":"https://orcid.org/0000-0001-6272-7668"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiben Yan","raw_affiliation_strings":["Michigan State University, East Lansing, US"],"raw_orcid":"https://orcid.org/0000-0001-6272-7668","affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, US","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100630881","display_name":"Li Xiao","orcid":"https://orcid.org/0000-0003-2861-8438"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Xiao","raw_affiliation_strings":["Michigan State University, East Lansing, USA"],"raw_orcid":"https://orcid.org/0000-0003-2861-8438","affiliations":[{"raw_affiliation_string":"Michigan State University, East Lansing, USA","institution_ids":["https://openalex.org/I87216513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5035545617"],"corresponding_institution_ids":["https://openalex.org/I117965899","https://openalex.org/I87216513"],"apc_list":null,"apc_paid":null,"fwci":0.2381,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55197754,"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":"1268","last_page":"1282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.991100013256073,"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"}},"topics":[{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.991100013256073,"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/T11309","display_name":"Music and Audio Processing","score":0.9708999991416931,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9591000080108643,"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":0.8037863969802856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7093477845191956},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5757569074630737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38906654715538025},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3556203842163086}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8037863969802856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7093477845191956},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5757569074630737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38906654715538025},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3556203842163086},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3636534.3690692","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3636534.3690692","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3636534.3690692","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th Annual International Conference on Mobile Computing and Networking","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3636534.3690692","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3636534.3690692","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3636534.3690692","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th Annual International Conference on Mobile Computing and Networking","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3354185911","display_name":null,"funder_award_id":"CNS-2310207","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5030741915","display_name":null,"funder_award_id":"CCF-2007159","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4405014384.pdf"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1974387177","https://openalex.org/W2964301649","https://openalex.org/W2973252307","https://openalex.org/W3006816054","https://openalex.org/W3007913795","https://openalex.org/W3036167779","https://openalex.org/W3109668151","https://openalex.org/W3162926177","https://openalex.org/W4205658643","https://openalex.org/W4286901099","https://openalex.org/W4287121833","https://openalex.org/W4306179629","https://openalex.org/W4308642081","https://openalex.org/W4382202529","https://openalex.org/W4387212527","https://openalex.org/W4387321684","https://openalex.org/W6779823529","https://openalex.org/W6795288823","https://openalex.org/W6796588791","https://openalex.org/W6802302390"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492"],"abstract_inverted_index":{"In":[0,146],"this":[1,52],"paper,":[2],"we":[3,102,132,148,158],"propose":[4],"WavePurifier,":[5,131],"an":[6],"audio":[7,13,111],"purification":[8,219],"framework":[9],"to":[10,24,45,54,67,108,123],"defend":[11,109],"against":[12,110,177,222],"adversarial":[14,17,20,69,112,135,140],"attacks.":[15,224],"Audio":[16],"attacks":[18,39,141,195],"craft":[19],"examples":[21,136],"or":[22,47],"perturbations":[23],"attack":[25,172],"the":[26,55,73,80,85,92,128,134,197,206],"automated":[27],"speech":[28],"recognition":[29],"(ASR)":[30],"models.":[31],"Although":[32],"existing":[33,63,179,203],"defense":[34,180],"mechanisms":[35],"can":[36],"detect":[37],"such":[38],"and":[40,153,174,216],"raise":[41],"alarms,":[42],"they":[43],"fail":[44],"recover":[46],"maintain":[48],"benign":[49,59,75,97],"commands.":[50,60,76],"Consequently,":[51],"leads":[53],"denial":[56],"of":[57,84,118,130],"users'":[58],"Different":[61],"than":[62],"defenses,":[64],"WavePurifier":[65,160,186,201],"aims":[66],"purify":[68,133],"examples,":[70],"thereby":[71],"rectifying":[72],"user's":[74],"We":[77],"find":[78],"that":[79,185],"forward":[81],"diffusion":[82,86,94,106],"process":[83,95],"model":[87,107,115],"effectively":[88],"eliminates":[89],"perturbations,":[90],"whereas":[91],"reverse":[93],"restores":[96],"speech.":[98],"Based":[99],"on":[100,161],"this,":[101],"develop":[103],"a":[104,188,217],"hierarchical":[105],"examples.":[113],"This":[114],"is":[116,187],"capable":[117],"purifying":[119],"different":[120,139,163,223],"spectrogram":[121],"bands":[122],"varying":[124],"degrees.":[125],"To":[126],"validate":[127],"performance":[129],"from":[137],"3":[138],"in":[142],"140":[143],"distinct":[144],"settings.":[145],"total,":[147],"collect":[149],"78,864":[150],"diffused":[151],"spectrograms":[152],"21,000":[154],"purified":[155],"audios.":[156],"Then,":[157],"evaluate":[159],"2":[162,170],"ASR":[164],"models,":[165],"4":[166],"commercial":[167],"speech-to-text":[168],"APIs,":[169],"real-world":[171],"scenarios,":[173],"compare":[175],"them":[176],"7":[178],"approaches.":[181],"Our":[182],"result":[183],"shows":[184],"universal":[189],"framework,":[190],"demonstrating":[191],"adaptability":[192],"across":[193],"diverse":[194],"with":[196,205],"same":[198],"hyperparameters.":[199],"Notably,":[200],"outperforms":[202],"methods":[204],"lowest":[207],"character":[208],"error":[209,213],"rate":[210,214,221],"(CER),":[211],"word":[212],"(WER),":[215],"high":[218],"success":[220]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}