{"id":"https://openalex.org/W4402593794","doi":"https://doi.org/10.1109/avss61716.2024.10672620","title":"Effective Adversarial Sample Detection for Securing Automatic Speech Recognition","display_name":"Effective Adversarial Sample Detection for Securing Automatic Speech Recognition","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4402593794","doi":"https://doi.org/10.1109/avss61716.2024.10672620"},"language":"en","primary_location":{"id":"doi:10.1109/avss61716.2024.10672620","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/avss61716.2024.10672620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)","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/A5087964642","display_name":"Chih\u2010Yang Lin","orcid":"https://orcid.org/0000-0002-0401-8473"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chih-Yang Lin","raw_affiliation_strings":["National Central University,Department of Mechanical Engineering,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Central University,Department of Mechanical Engineering,Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783277","display_name":"Yanzhang Wang","orcid":"https://orcid.org/0000-0002-7016-9624"},"institutions":[{"id":"https://openalex.org/I148099254","display_name":"National Chung Cheng University","ror":"https://ror.org/0028v3876","country_code":"TW","type":"education","lineage":["https://openalex.org/I148099254"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yan-Zhang Wang","raw_affiliation_strings":["National Chung Cheng University,Department of Computer Science and Information Engineering,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Chung Cheng University,Department of Computer Science and Information Engineering,Taiwan","institution_ids":["https://openalex.org/I148099254"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114228401","display_name":"Shou-Kuan Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shou-Kuan Lin","raw_affiliation_strings":["Yoder International Academy,Taoyuan,Taiwan"],"affiliations":[{"raw_affiliation_string":"Yoder International Academy,Taoyuan,Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050605490","display_name":"Isack Farady","orcid":"https://orcid.org/0000-0003-1160-8890"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Isack Farady","raw_affiliation_strings":["National Central University,Department of Mechanical Engineering,Taiwan"],"affiliations":[{"raw_affiliation_string":"National Central University,Department of Mechanical Engineering,Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080909004","display_name":"Yih\u2010Kuen Jan","orcid":"https://orcid.org/0000-0001-7149-4034"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yih-Kuen Jan","raw_affiliation_strings":["University of Illinois at Urbana-Champaign,Rehabilitation Engineering Lab, College of Applied Health Sciences,USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign,Rehabilitation Engineering Lab, College of Applied Health Sciences,USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101420358","display_name":"Wei-Yang Lin","orcid":"https://orcid.org/0000-0003-0895-2498"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei-Yang Lin","raw_affiliation_strings":["University of Illinois at Urbana-Champaign,Rehabilitation Engineering Lab,USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign,Rehabilitation Engineering Lab,USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5087964642"],"corresponding_institution_ids":["https://openalex.org/I22265921"],"apc_list":null,"apc_paid":null,"fwci":0.275,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53686542,"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":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.947700023651123,"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":0.947700023651123,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9429000020027161,"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":0.9136000275611877,"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/adversarial-system","display_name":"Adversarial system","score":0.8206062316894531},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.750962495803833},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6227515339851379},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5761549472808838},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4620823860168457},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3746753931045532}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8206062316894531},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.750962495803833},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6227515339851379},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5761549472808838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4620823860168457},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3746753931045532},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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":1,"locations":[{"id":"doi:10.1109/avss61716.2024.10672620","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/avss61716.2024.10672620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331164","display_name":"National Science and Technology Council","ror":"https://ror.org/00wnb9798"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1757980361","https://openalex.org/W2100495367","https://openalex.org/W2119821739","https://openalex.org/W2603766943","https://openalex.org/W2962747881","https://openalex.org/W2964301649","https://openalex.org/W2997395473","https://openalex.org/W3017720918","https://openalex.org/W3153453329","https://openalex.org/W4300672471","https://openalex.org/W4311424365","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6687566353","https://openalex.org/W6729756640","https://openalex.org/W6739868092","https://openalex.org/W6754602573","https://openalex.org/W6755779437","https://openalex.org/W6929233984"],"related_works":["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","https://openalex.org/W4310988119","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Deep":[0],"learning":[1,56],"has":[2],"emerged":[3],"as":[4,36],"a":[5,24],"pivotal":[6],"technology":[7],"across":[8],"various":[9],"domains,":[10],"demonstrating":[11],"remarkable":[12],"performance.":[13],"However,":[14],"its":[15],"susceptibility":[16],"to":[17,47,70,81,93],"security":[18],"threats,":[19],"particularly":[20],"adversarial":[21,75,100,141],"samples,":[22],"poses":[23],"significant":[25],"concern.":[26],"These":[27],"samples":[28,101,143],"can":[29,138],"manipulate":[30],"inputs":[31],"slightly,":[32],"deceiving":[33],"models":[34],"such":[35],"those":[37],"used":[38],"in":[39,57,113],"image":[40],"or":[41,130],"speech":[42,82,127],"recognition":[43,83,128],"and":[44,72],"potentially":[45],"leading":[46],"incorrect":[48],"predictions.":[49],"This":[50],"undermines":[51],"the":[52,95,114,124],"reliability":[53],"of":[54],"deep":[55],"critical":[58],"applications.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"propose":[64],"an":[65],"effective":[66],"method":[67,117],"utilizing":[68],"Autoencoder":[69,96],"detect":[71],"intercept":[73],"audio":[74,91],"attacks":[76],"before":[77],"they":[78],"are":[79],"input":[80],"models.":[84],"The":[85],"proposed":[86],"approach":[87],"first":[88],"uses":[89],"clean":[90,103,145],"data":[92],"train":[94],"model,":[97],"then":[98],"isolates":[99],"from":[102,144],"ones":[104,146],"by":[105],"comparing":[106],"their":[107],"features":[108,111],"against":[109],"normal":[110],"encoded":[112],"Autoencoder.":[115],"Our":[116],"does":[118],"not":[119],"require":[120],"prior":[121],"knowledge":[122],"about":[123],"target":[125],"automatic":[126],"model":[129],"attack":[131,142],"methods.":[132],"Experimental":[133],"results":[134],"show":[135],"that":[136],"it":[137],"effectively":[139],"discriminate":[140],"with":[147],"high":[148],"accuracy.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}