{"id":"https://openalex.org/W4372260558","doi":"https://doi.org/10.1109/icassp49357.2023.10096873","title":"Transaudio: Towards the Transferable Adversarial Audio Attack Via Learning Contextualized Perturbations","display_name":"Transaudio: Towards the Transferable Adversarial Audio Attack Via Learning Contextualized Perturbations","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260558","doi":"https://doi.org/10.1109/icassp49357.2023.10096873"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5017490346","display_name":"Gege Qi","orcid":"https://orcid.org/0000-0002-0032-6786"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gege Qi","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042884230","display_name":"Yuefeng Chen","orcid":"https://orcid.org/0000-0002-5925-2291"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuefeng Chen","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101567069","display_name":"Yao Zhu","orcid":"https://orcid.org/0000-0003-0991-1970"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Zhu","raw_affiliation_strings":["Zhejiang University,Hangzhou,China","Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,Hangzhou,China","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080628250","display_name":"Binyuan Hui","orcid":"https://orcid.org/0000-0002-2160-7595"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binyuan Hui","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100433314","display_name":"Xiaodan Li","orcid":"https://orcid.org/0000-0002-5025-4805"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Li","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051298007","display_name":"Xiaofeng Mao","orcid":"https://orcid.org/0000-0003-4486-556X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Mao","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451786","display_name":"Rong Zhang","orcid":"https://orcid.org/0000-0002-2288-2847"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rong Zhang","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050108117","display_name":"Hui Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Xue","raw_affiliation_strings":["Alibaba Group,Hangzhou,China","Alibaba Group, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Alibaba Group,Hangzhou,China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5017490346"],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":0.8741,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77874434,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994999766349792,"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":0.9994999766349792,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9764999747276306,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9749000072479248,"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":0.8370583057403564},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8347935676574707},{"id":"https://openalex.org/keywords/transferability","display_name":"Transferability","score":0.6451552510261536},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5346900820732117},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5328545570373535},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5298447608947754},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4411359429359436},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.41413968801498413},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38882672786712646},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.29514580965042114}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8370583057403564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8347935676574707},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.6451552510261536},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5346900820732117},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5328545570373535},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5298447608947754},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4411359429359436},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.41413968801498413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38882672786712646},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29514580965042114},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096873","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2526425061","https://openalex.org/W2774644650","https://openalex.org/W2962717526","https://openalex.org/W2962780374","https://openalex.org/W2962847335","https://openalex.org/W2963242190","https://openalex.org/W2964301649","https://openalex.org/W2973057252","https://openalex.org/W3033411150","https://openalex.org/W3093904722","https://openalex.org/W3101527329","https://openalex.org/W3138740729","https://openalex.org/W3169948074","https://openalex.org/W3207651366","https://openalex.org/W4200444305","https://openalex.org/W4304701424","https://openalex.org/W6748288002","https://openalex.org/W6765450635","https://openalex.org/W6778823374","https://openalex.org/W6780164432","https://openalex.org/W6783248943"],"related_works":["https://openalex.org/W4288055406","https://openalex.org/W3137894200","https://openalex.org/W3092178728","https://openalex.org/W4226402597","https://openalex.org/W4200630034","https://openalex.org/W3132910851","https://openalex.org/W4377864639","https://openalex.org/W2997056298","https://openalex.org/W2950864148","https://openalex.org/W2570685808"],"abstract_inverted_index":{"In":[0],"a":[1,52],"transfer-based":[2],"attack":[3,24,55,79],"against":[4,112],"Automatic":[5],"Speech":[6],"Recognition":[7],"(ASR)":[8],"systems,":[9],"attacks":[10,69],"are":[11,26],"unable":[12],"to":[13,40,89,99],"access":[14],"the":[15,20,72,78,91,100,108],"architecture":[16],"and":[17,59,105,116],"parameters":[18],"of":[19,110],"target":[21],"model.":[22,102],"Existing":[23],"methods":[25],"mostly":[27],"investigated":[28],"in":[29],"voice":[30,35],"assistant":[31],"scenarios":[32],"with":[33,56],"restricted":[34],"commands,":[36],"prohibiting":[37],"their":[38],"applicability":[39],"more":[41],"general":[42],"ASR":[43,114],"related":[44],"applications.":[45],"To":[46,76],"tackle":[47],"this":[48],"challenge,":[49],"we":[50,81],"propose":[51],"novel":[53],"contextualized":[54],"deletion,":[57],"insertion,":[58],"substitution":[60],"adversarial":[61,96],"behaviors,":[62],"namely":[63],"TransAudio,":[64],"which":[65,94],"achieves":[66],"arbitrary":[67],"word-level":[68],"based":[70],"on":[71],"proposed":[73],"two-stage":[74],"framework.":[75],"strengthen":[77],"transferability,":[80],"further":[82],"introduce":[83],"an":[84],"audio":[85],"score-matching":[86],"optimization":[87],"strategy":[88],"regularize":[90],"training":[92],"process,":[93],"mitigates":[95],"example":[97],"over-fitting":[98],"surrogate":[101],"Extensive":[103],"experiments":[104],"analysis":[106],"demonstrate":[107],"effectiveness":[109],"TransAudio":[111],"open-source":[113],"models":[115],"commercial":[117],"APIs.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
