{"id":"https://openalex.org/W4319862411","doi":"https://doi.org/10.1109/slt54892.2023.10022646","title":"Push-Pull: Characterizing the Adversarial Robustness for Audio-Visual Active Speaker Detection","display_name":"Push-Pull: Characterizing the Adversarial Robustness for Audio-Visual Active Speaker Detection","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862411","doi":"https://doi.org/10.1109/slt54892.2023.10022646"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022646","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022646","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5051463746","display_name":"Xuanjun Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Xuanjun Chen","raw_affiliation_strings":["National Taiwan University,Department. of Computer Science Information Engineering","Department. of Computer Science Information Engineering, National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Department. of Computer Science Information Engineering","institution_ids":["https://openalex.org/I16733864","https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Department. of Computer Science Information Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101474128","display_name":"Haibin Wu","orcid":"https://orcid.org/0000-0001-7166-5534"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK","TW"],"is_corresponding":false,"raw_author_name":"Haibin Wu","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University","Centre for Perceptual and Interactive Intelligence, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Centre for Perceptual and Interactive Intelligence","Human-Computer Communications Laboratory, The Chinese University of Hong Kong","Centre for Perceptual and Interactive Intelligence, The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Centre for Perceptual and Interactive Intelligence","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Human-Computer Communications Laboratory, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Centre for Perceptual and Interactive Intelligence, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073451247","display_name":"Jyh\u2010Shing Roger Jang","orcid":"https://orcid.org/0000-0002-7319-9095"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]},{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jyh-Shing Roger Jang","raw_affiliation_strings":["National Taiwan University,Department. of Computer Science Information Engineering","Department. of Computer Science Information Engineering, National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Department. of Computer Science Information Engineering","institution_ids":["https://openalex.org/I16733864","https://openalex.org/I4210098366"]},{"raw_affiliation_string":"Department. of Computer Science Information Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"692","last_page":"699"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9708999991416931,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9689000248908997,"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":0.8468056321144104},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.8415602445602417},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8244724273681641},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.7330477833747864},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6396296620368958},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6349518895149231},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.49387484788894653},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4874008297920227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4297560751438141},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.16994521021842957}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8468056321144104},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8415602445602417},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8244724273681641},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.7330477833747864},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6396296620368958},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6349518895149231},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.49387484788894653},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4874008297920227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4297560751438141},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.16994521021842957},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022646","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/slt54892.2023.10022646","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1583773829","https://openalex.org/W1673923490","https://openalex.org/W1945616565","https://openalex.org/W2243397390","https://openalex.org/W2774644650","https://openalex.org/W2782403400","https://openalex.org/W2792351646","https://openalex.org/W2898435086","https://openalex.org/W2954458766","https://openalex.org/W2962747881","https://openalex.org/W2963058500","https://openalex.org/W2964301649","https://openalex.org/W2972532204","https://openalex.org/W2973252307","https://openalex.org/W3006808893","https://openalex.org/W3007679772","https://openalex.org/W3014522660","https://openalex.org/W3015958938","https://openalex.org/W3016098309","https://openalex.org/W3016138785","https://openalex.org/W3024085360","https://openalex.org/W3027378069","https://openalex.org/W3034702511","https://openalex.org/W3039832962","https://openalex.org/W3054852761","https://openalex.org/W3095259706","https://openalex.org/W3096171739","https://openalex.org/W3119269912","https://openalex.org/W3128911095","https://openalex.org/W3131867595","https://openalex.org/W3155956353","https://openalex.org/W3162096084","https://openalex.org/W3162258435","https://openalex.org/W3169351047","https://openalex.org/W3172472082","https://openalex.org/W3173081491","https://openalex.org/W3189964604","https://openalex.org/W3197694255","https://openalex.org/W3198570670","https://openalex.org/W3206008172","https://openalex.org/W3207207922","https://openalex.org/W3207460178","https://openalex.org/W4214701094","https://openalex.org/W4225297350","https://openalex.org/W4226416815","https://openalex.org/W4253732063","https://openalex.org/W4285094241","https://openalex.org/W4287063346","https://openalex.org/W4289665794","https://openalex.org/W4293846201","https://openalex.org/W4312466984","https://openalex.org/W4312638101","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6739868092","https://openalex.org/W6746882984","https://openalex.org/W6760326341","https://openalex.org/W6765195009","https://openalex.org/W6799852253"],"related_works":["https://openalex.org/W4303857474","https://openalex.org/W4319862411","https://openalex.org/W4302011902","https://openalex.org/W2116497041","https://openalex.org/W4304891817","https://openalex.org/W3098984791","https://openalex.org/W4287598323","https://openalex.org/W3203028475","https://openalex.org/W4292267426","https://openalex.org/W2155289555"],"abstract_inverted_index":{"Audio-visual":[0],"active":[1],"speaker":[2],"detection":[3],"(AVASD)":[4],"is":[5,9],"well-developed,":[6],"and":[7,59,104,109],"now":[8],"an":[10,87],"indispensable":[11],"front-end":[12],"for":[13,77],"several":[14],"multi-modal":[15,136],"applications.":[16],"However,":[17],"to":[18,34,49,81,99,118],"the":[19,24,36,47,51,96,111,125,128],"best":[20],"of":[21,27,53],"our":[22],"knowledge,":[23],"adversarial":[25,61,84,129],"robustness":[26],"AVASD":[28,54],"models":[29,55],"hasn't":[30],"been":[31],"investigated,":[32],"not":[33],"mention":[35],"effective":[37],"defense":[38],"against":[39],"such":[40],"attacks.":[41,137],"In":[42],"this":[43],"paper,":[44],"we":[45,68],"are":[46],"first":[48],"reveal":[50],"vulnerability":[52],"under":[56,86,135],"audio-only,":[57],"visual-only,":[58],"audio-visual":[60,73],"attacks":[62],"through":[63],"extensive":[64],"experiments.":[65],"What's":[66],"more,":[67],"also":[69],"propose":[70],"a":[71],"novel":[72],"interaction":[74],"loss":[75,92],"(AVIL)":[76],"making":[78],"attackers":[79],"difficult":[80],"find":[82],"feasible":[83],"examples":[85],"allocated":[88],"attack":[89],"budget.":[90],"The":[91],"aims":[93],"at":[94],"pushing":[95],"inter-class":[97],"embeddings":[98,113],"be":[100],"dispersed,":[101],"namely":[102],"non-speech":[103],"speech":[105],"clusters,":[106],"sufficiently":[107],"disentangled,":[108],"pulling":[110],"intra-class":[112],"as":[114,116],"close":[115],"possible":[117],"keep":[119],"them":[120],"compact.":[121],"Experimental":[122],"results":[123],"show":[124],"AVIL":[126],"outperforms":[127],"training":[130],"by":[131],"33.14":[132],"mAP":[133],"(%)":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}