{"id":"https://openalex.org/W4290943474","doi":"https://doi.org/10.1145/3534678.3539268","title":"Synthesising Audio Adversarial Examples for Automatic Speech Recognition","display_name":"Synthesising Audio Adversarial Examples for Automatic Speech Recognition","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W4290943474","doi":"https://doi.org/10.1145/3534678.3539268"},"language":"en","primary_location":{"id":"doi:10.1145/3534678.3539268","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539268","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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/A5010723706","display_name":"Xinghua Qu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xinghua Qu","raw_affiliation_strings":["Bytedance AI Lab, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101506669","display_name":"Pengfei Wei","orcid":"https://orcid.org/0000-0001-8093-0803"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengfei Wei","raw_affiliation_strings":["Bytedance AI Lab, Sinagpore, Singapore"],"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab, Sinagpore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002678674","display_name":"Ming-yong Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingyong Gao","raw_affiliation_strings":["University of Science and Technology of China, Hefei, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033957641","display_name":"Zhu Sun","orcid":"https://orcid.org/0000-0002-3350-7022"},"institutions":[{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhu Sun","raw_affiliation_strings":["Institute of High Performance Computing and Centre for Frontier AI Research & A*STAR, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing and Centre for Frontier AI Research & A*STAR, Singapore, Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068243197","display_name":"Yew-Soon Ong","orcid":"https://orcid.org/0000-0002-4480-169X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yew Soon Ong","raw_affiliation_strings":["Nanyang Technological University & A*STAR Centre for Frontier AI Research, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University & A*STAR Centre for Frontier AI Research, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110851569","display_name":"Zejun Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zejun Ma","raw_affiliation_strings":["Bytedance AI Lab, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5010723706"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7271,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.70932989,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1430","last_page":"1440"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9968000054359436,"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":0.9968000054359436,"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":0.9961000084877014,"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/T11309","display_name":"Music and Audio Processing","score":0.9886000156402588,"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/computer-science","display_name":"Computer science","score":0.7905792593955994},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7217721343040466},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.6685138940811157},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.6126195192337036},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.486519992351532},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4630807340145111},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.44669175148010254},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4404488205909729},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40359461307525635},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3309060335159302},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3227083384990692},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12572887539863586},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08044347167015076}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7905792593955994},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7217721343040466},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.6685138940811157},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.6126195192337036},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.486519992351532},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4630807340145111},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.44669175148010254},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4404488205909729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40359461307525635},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3309060335159302},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3227083384990692},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12572887539863586},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08044347167015076},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3534678.3539268","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3534678.3539268","pdf_url":null,"source":{"id":"https://openalex.org/S4363608767","display_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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":"conference"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W569478347","https://openalex.org/W1494198834","https://openalex.org/W1979356488","https://openalex.org/W2108598243","https://openalex.org/W2127141656","https://openalex.org/W2156279557","https://openalex.org/W2327501763","https://openalex.org/W2560674852","https://openalex.org/W2747329762","https://openalex.org/W2766447205","https://openalex.org/W2890591829","https://openalex.org/W2898435086","https://openalex.org/W2962780374","https://openalex.org/W2964243274","https://openalex.org/W2964301649","https://openalex.org/W2973057252","https://openalex.org/W2973252307","https://openalex.org/W2997395473","https://openalex.org/W3000716014","https://openalex.org/W3006816054","https://openalex.org/W3008307122","https://openalex.org/W3015001695","https://openalex.org/W3017720918","https://openalex.org/W4230167402","https://openalex.org/W4300824008","https://openalex.org/W6836725202"],"related_works":["https://openalex.org/W2374918184","https://openalex.org/W3151376046","https://openalex.org/W1987021544","https://openalex.org/W82600882","https://openalex.org/W2793122029","https://openalex.org/W4249316903","https://openalex.org/W3166169565","https://openalex.org/W2948132774","https://openalex.org/W1501126083","https://openalex.org/W4372270126"],"abstract_inverted_index":{"Adversarial":[0],"examples":[1,26,68,135],"in":[2],"automatic":[3],"speech":[4,96],"recognition":[5],"(ASR)":[6],"are":[7,27,40],"naturally":[8,131],"sounded":[9,132],"by":[10,30],"humans":[11],"yet":[12],"capable":[13],"of":[14],"fooling":[15],"well":[16],"trained":[17],"ASR":[18,82,140],"models":[19],"to":[20,79,107,136],"transcribe":[21],"incorrectly.":[22],"Existing":[23],"audio":[24,36,45,66,78,111,133,146],"adversarial":[25,67,110,134],"typically":[28],"constructed":[29],"adding":[31],"constrained":[32],"perturbations":[33],"on":[34,75,115],"benign":[35],"inputs.":[37],"Such":[38],"attacks":[39],"therefore":[41],"generated":[42,145],"with":[43],"an":[44,99],"dependent":[46],"assumption.":[47],"For":[48],"the":[49,54,95,109,138],"first":[50],"time,":[51],"we":[52,87],"propose":[53],"Speech":[55],"Synthesising":[56],"based":[57],"Attack":[58],"(SSA),":[59],"a":[60,89],"novel":[61],"threat":[62],"model":[63],"that":[64,126],"constructs":[65],"entirely":[69],"from":[70],"scratch,":[71],"i.e.,":[72],"without":[73],"depending":[74],"any":[76],"existing":[77],"fool":[80],"cutting-edge":[81],"models.":[83,141],"To":[84],"this":[85],"end,":[86],"introduce":[88],"conditional":[90],"variational":[91],"auto-encoder":[92],"(CVAE)":[93],"as":[94],"synthesiser.":[97],"Meanwhile,":[98],"adaptive":[100],"sign":[101],"gradient":[102],"descent":[103],"algorithm":[104],"is":[105,148],"proposed":[106],"solve":[108],"synthesis":[112],"task.":[113],"Experiments":[114],"three":[116],"datasets":[117],"(i.e.,":[118],"Audio":[119],"Mnist,":[120],"Common":[121],"Voice,":[122],"and":[123],"Librispeech)":[124],"show":[125],"our":[127],"method":[128],"could":[129],"synthesise":[130],"mislead":[137],"start-of-the-art":[139],"Our":[142],"web-page":[143],"containing":[144],"demos":[147],"at":[149],"https://sites.google.com/view/ssa-asr/home.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}