{"id":"https://openalex.org/W4415708219","doi":"https://doi.org/10.1109/icme59968.2025.11210179","title":"Selective Masking Adversarial Attack on Automatic Speech Recognition Systems","display_name":"Selective Masking Adversarial Attack on Automatic Speech Recognition Systems","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708219","doi":"https://doi.org/10.1109/icme59968.2025.11210179"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11210179","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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/A5114860542","display_name":"Zheng Fang","orcid":"https://orcid.org/0009-0005-9308-7452"},"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":true,"raw_author_name":"Zheng Fang","raw_affiliation_strings":["Wuhan University,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Wuhan University,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103231923","display_name":"Shenyi Zhang","orcid":"https://orcid.org/0009-0000-2140-7131"},"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":"Shenyi Zhang","raw_affiliation_strings":["Wuhan University,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Wuhan University,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114860300","display_name":"Tao Wang","orcid":"https://orcid.org/0000-0002-5265-1521"},"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":"Tao Wang","raw_affiliation_strings":["Wuhan University,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Wuhan University,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114860632","display_name":"Bowen Li","orcid":"https://orcid.org/0009-0004-5445-8209"},"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":"Bowen Li","raw_affiliation_strings":["Wuhan University,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Wuhan University,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030015523","display_name":"Lingchen Zhao","orcid":"https://orcid.org/0000-0002-1700-3836"},"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":"Lingchen Zhao","raw_affiliation_strings":["Wuhan University,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Wuhan University,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101680716","display_name":"Zhangyi Wang","orcid":"https://orcid.org/0000-0003-1494-7476"},"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":"Zhangyi Wang","raw_affiliation_strings":["Wuhan University,Wuhan,China"],"affiliations":[{"raw_affiliation_string":"Wuhan University,Wuhan,China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5114860542"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17520657,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9746000170707703,"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":0.9746000170707703,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.003100000089034438,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.0024999999441206455,"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":0.7894999980926514},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.682699978351593},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4277999997138977},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.41600000858306885},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3878999948501587},{"id":"https://openalex.org/keywords/sma*","display_name":"SMA*","score":0.32010000944137573},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31369999051094055},{"id":"https://openalex.org/keywords/auditory-masking","display_name":"Auditory masking","score":0.3052999973297119}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7894999980926514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7739999890327454},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7250000238418579},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.682699978351593},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4277999997138977},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.41600000858306885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4101000130176544},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C161921814","wikidata":"https://www.wikidata.org/wiki/Q493743","display_name":"SMA*","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C77801330","wikidata":"https://www.wikidata.org/wiki/Q1363413","display_name":"Auditory masking","level":3,"score":0.3052999973297119},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.27390000224113464},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.272599995136261},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.2630999982357025}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11210179","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11210179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":18,"referenced_works":["https://openalex.org/W1995562189","https://openalex.org/W2127141656","https://openalex.org/W2556345765","https://openalex.org/W2963477857","https://openalex.org/W2964301649","https://openalex.org/W2972389417","https://openalex.org/W2973215447","https://openalex.org/W2973252307","https://openalex.org/W3015537910","https://openalex.org/W3016010032","https://openalex.org/W3088377098","https://openalex.org/W3095173472","https://openalex.org/W3097777922","https://openalex.org/W3155956353","https://openalex.org/W3207651366","https://openalex.org/W3209059054","https://openalex.org/W4372260558","https://openalex.org/W4405181112"],"related_works":[],"abstract_inverted_index":{"Extensive":[0,109],"research":[1],"has":[2],"shown":[3],"that":[4,48,112],"Automatic":[5],"Speech":[6],"Recognition":[7],"(ASR)":[8],"systems":[9],"are":[10,29],"vulnerable":[11],"to":[12,69],"audio":[13,50,59,80,84,121],"adversarial":[14,92,122],"attacks.":[15],"Current":[16],"attacks":[17],"mainly":[18],"focus":[19],"on":[20,142],"single-source":[21],"scenarios,":[22],"ignoring":[23],"dual-source":[24,64,71,79,126],"scenarios":[25],"where":[26],"two":[27],"people":[28],"speaking":[30],"simultaneously.":[31],"To":[32,66],"bridge":[33],"the":[34,57,70,77,82,91,113,125,145],"gap,":[35],"we":[36],"propose":[37],"a":[38,95,104],"Selective":[39],"Masking":[40],"Adversarial":[41],"attack,":[42,45],"namely":[43],"SMA":[44,74,88,114],"which":[46],"ensures":[47],"one":[49],"source":[51,60],"is":[52,61],"selected":[53,86],"for":[54],"recognition":[55],"while":[56],"other":[58],"muted":[62,83],"in":[63,124],"scenarios.":[65],"better":[67],"adapt":[68],"scenario,":[72,127],"our":[73],"attack":[75,89,115,134],"constructs":[76],"normal":[78],"from":[81],"and":[85,99,119,137],"audio.":[87],"initializes":[90],"perturbation":[93],"with":[94],"small":[96],"Gaus-sian":[97],"noise":[98],"iteratively":[100],"optimizes":[101],"it":[102],"using":[103],"selective":[105],"masking":[106],"optimization":[107],"algorithm.":[108],"experiments":[110],"demonstrate":[111],"can":[116],"generate":[117],"effective":[118],"imperceptible":[120],"examples":[123],"achieving":[128],"an":[129],"average":[130],"success":[131],"rate":[132],"of":[133,135,140],"100%":[136],"signal-to-noise":[138],"ratio":[139],"37.15dB":[141],"Conformer-CTC,":[143],"outperforming":[144],"baselines.":[146]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-30T00:00:00"}