{"id":"https://openalex.org/W4391841779","doi":"https://doi.org/10.3389/fcomp.2024.1355975","title":"Phantom in the opera: adversarial music attack for robot dialogue system","display_name":"Phantom in the opera: adversarial music attack for robot dialogue system","publication_year":2024,"publication_date":"2024-02-15","ids":{"openalex":"https://openalex.org/W4391841779","doi":"https://doi.org/10.3389/fcomp.2024.1355975"},"language":"en","primary_location":{"id":"doi:10.3389/fcomp.2024.1355975","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fcomp.2024.1355975","pdf_url":"https://www.frontiersin.org/articles/10.3389/fcomp.2024.1355975/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S4210211086","display_name":"Frontiers in Computer Science","issn_l":"2624-9898","issn":["2624-9898"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Computer Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/articles/10.3389/fcomp.2024.1355975/pdf?isPublishedV2=False","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Sheng Li","raw_affiliation_strings":["National Institute of Information and Communications Technology, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067208985","display_name":"Jiyi Li","orcid":"https://orcid.org/0000-0003-4997-3850"},"institutions":[{"id":"https://openalex.org/I66906201","display_name":"University of Yamanashi","ror":"https://ror.org/059x21724","country_code":"JP","type":"education","lineage":["https://openalex.org/I66906201"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jiyi Li","raw_affiliation_strings":["University of Yamanashi, Kofu, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Yamanashi, Kofu, Japan","institution_ids":["https://openalex.org/I66906201"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082946615","display_name":"Yang Cao","orcid":"https://orcid.org/0000-0002-6424-8633"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yang Cao","raw_affiliation_strings":["Hokkaido University, Sapporo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053726259"],"corresponding_institution_ids":["https://openalex.org/I90023481"],"apc_list":{"value":1285,"currency":"USD","value_usd":1285},"apc_paid":{"value":1285,"currency":"USD","value_usd":1285},"fwci":0.486,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.686001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"6","issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962999820709229,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9962999820709229,"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":0.9918000102043152,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9890000224113464,"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/opera","display_name":"Opera","score":0.8306031227111816},{"id":"https://openalex.org/keywords/imaging-phantom","display_name":"Imaging phantom","score":0.790871262550354},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7679175138473511},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.47312062978744507},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4210319221019745},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.3874218761920929},{"id":"https://openalex.org/keywords/visual-arts","display_name":"Visual arts","score":0.3032993674278259},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26826655864715576},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11017367243766785},{"id":"https://openalex.org/keywords/optics","display_name":"Optics","score":0.08229079842567444}],"concepts":[{"id":"https://openalex.org/C530479602","wikidata":"https://www.wikidata.org/wiki/Q1344","display_name":"Opera","level":2,"score":0.8306031227111816},{"id":"https://openalex.org/C104293457","wikidata":"https://www.wikidata.org/wiki/Q28324852","display_name":"Imaging phantom","level":2,"score":0.790871262550354},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7679175138473511},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.47312062978744507},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4210319221019745},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.3874218761920929},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.3032993674278259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26826655864715576},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11017367243766785},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.08229079842567444}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3389/fcomp.2024.1355975","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fcomp.2024.1355975","pdf_url":"https://www.frontiersin.org/articles/10.3389/fcomp.2024.1355975/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S4210211086","display_name":"Frontiers in Computer Science","issn_l":"2624-9898","issn":["2624-9898"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Computer Science","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:e3c4a1535d8946e7bda03e365cd86ed6","is_oa":false,"landing_page_url":"https://doaj.org/article/e3c4a1535d8946e7bda03e365cd86ed6","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Computer Science, Vol 6 (2024)","raw_type":"article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50728041","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100930619","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.3389/fcomp.2024.1355975","is_oa":true,"landing_page_url":"https://doi.org/10.3389/fcomp.2024.1355975","pdf_url":"https://www.frontiersin.org/articles/10.3389/fcomp.2024.1355975/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S4210211086","display_name":"Frontiers in Computer Science","issn_l":"2624-9898","issn":["2624-9898"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G4390204761","display_name":null,"funder_award_id":"JP23K11227","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5208785282","display_name":"Learning Reliable Deep Models from Noise Labels by Crowdsourcing","funder_award_id":"23K28092","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8471687183","display_name":"M3OLR: Towards Effective Multilingual, Multimodal and Multitask Oriental Low-resourced Language Speech Recognition","funder_award_id":"23K11227","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4391841779.pdf"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1762484328","https://openalex.org/W1945616565","https://openalex.org/W2102113734","https://openalex.org/W2117671523","https://openalex.org/W2120847449","https://openalex.org/W2125838338","https://openalex.org/W2127141656","https://openalex.org/W2147768505","https://openalex.org/W2327501763","https://openalex.org/W2402146185","https://openalex.org/W2407080277","https://openalex.org/W2554972835","https://openalex.org/W2748659049","https://openalex.org/W2770312844","https://openalex.org/W2782403400","https://openalex.org/W2898435086","https://openalex.org/W2923292931","https://openalex.org/W2962717526","https://openalex.org/W2962780374","https://openalex.org/W2963058500","https://openalex.org/W2963077926","https://openalex.org/W2964301649","https://openalex.org/W2964323211","https://openalex.org/W3133764549","https://openalex.org/W4293846201","https://openalex.org/W4300824008","https://openalex.org/W4372340947","https://openalex.org/W4385823104","https://openalex.org/W6624852173","https://openalex.org/W6631362777","https://openalex.org/W6637956674","https://openalex.org/W6640425456","https://openalex.org/W6675365184","https://openalex.org/W6722479552","https://openalex.org/W6739868092","https://openalex.org/W6739901393","https://openalex.org/W6746295503","https://openalex.org/W6746882984","https://openalex.org/W6748288002","https://openalex.org/W6760326341","https://openalex.org/W6790750458"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2353500159","https://openalex.org/W2386740010","https://openalex.org/W3011881386","https://openalex.org/W635637022","https://openalex.org/W2348070968","https://openalex.org/W2377396514","https://openalex.org/W4246396837","https://openalex.org/W2482350142","https://openalex.org/W3176240006"],"abstract_inverted_index":{"This":[0,109],"study":[1],"explores":[2],"the":[3,59,102,106],"vulnerability":[4],"of":[5],"robot":[6,118],"dialogue":[7,119],"systems'":[8],"automatic":[9],"speech":[10,37,67],"recognition":[11],"(ASR)":[12],"module":[13],"to":[14,34,105,117],"adversarial":[15,75,115],"music":[16,21,41,76,104,116],"attacks.":[17,28,128],"Specifically,":[18],"we":[19],"explore":[20],"as":[22],"a":[23,31,40,111],"natural":[24],"camouflage":[25],"for":[26,66,122],"such":[27,126],"We":[29,49],"propose":[30],"novel":[32],"method":[33],"hide":[35],"ghost":[36,90],"commands":[38,91],"in":[39],"clip":[42],"by":[43,78,114],"slightly":[44],"perturbing":[45],"its":[46],"raw":[47],"waveform.":[48],"apply":[50],"our":[51,79],"attack":[52,80],"on":[53],"an":[54],"industry-popular":[55],"ASR":[56],"model,":[57],"namely":[58],"time-delay":[60],"neural":[61],"network":[62],"(TDNN),":[63],"widely":[64],"used":[65],"and":[68],"speaker":[69],"recognition.":[70],"Our":[71],"experiment":[72],"demonstrates":[73],"that":[74],"crafted":[77],"can":[81],"easily":[82],"mislead":[83],"industry-level":[84],"TDNN":[85],"models":[86],"into":[87],"picking":[88],"up":[89],"with":[92],"high":[93],"success":[94],"rates.":[95],"However,":[96],"it":[97],"sounds":[98],"no":[99],"different":[100],"from":[101],"original":[103],"human":[107],"ear.":[108],"reveals":[110],"serious":[112],"threat":[113],"systems,":[120],"calling":[121],"effective":[123],"defenses":[124],"against":[125],"stealthy":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}