{"id":"https://openalex.org/W4226416815","doi":"https://doi.org/10.1109/icassp43922.2022.9746124","title":"On Adversarial Robustness Of Large-Scale Audio Visual Learning","display_name":"On Adversarial Robustness Of Large-Scale Audio Visual Learning","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4226416815","doi":"https://doi.org/10.1109/icassp43922.2022.9746124"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746124","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5004697852","display_name":"Juncheng B Li","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juncheng B Li","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112694715","display_name":"Shuhui Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuhui Qu","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100660610","display_name":"Xinjian Li","orcid":"https://orcid.org/0000-0003-4585-159X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinjian Li","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063149046","display_name":"Po-Yao Huang","orcid":"https://orcid.org/0000-0002-3319-5145"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Po-Yao Bernie Huang","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.4623,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71019509,"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":"231","last_page":"235"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9954000115394592,"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":0.9954000115394592,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.995199978351593,"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":0.9944999814033508,"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/robustness","display_name":"Robustness (evolution)","score":0.745954692363739},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.726318895816803},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6817265748977661},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5022895336151123},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4810105264186859},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.43586471676826477}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.745954692363739},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.726318895816803},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6817265748977661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5022895336151123},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4810105264186859},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.43586471676826477},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746124","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W24089286","https://openalex.org/W2526050071","https://openalex.org/W2543927648","https://openalex.org/W2593116425","https://openalex.org/W2619383789","https://openalex.org/W2619697695","https://openalex.org/W2619947201","https://openalex.org/W2913848079","https://openalex.org/W2924630351","https://openalex.org/W2950048339","https://openalex.org/W2963155035","https://openalex.org/W2963496101","https://openalex.org/W2964116600","https://openalex.org/W2996564870","https://openalex.org/W3018979822","https://openalex.org/W3034537217","https://openalex.org/W3034726383","https://openalex.org/W3035333188","https://openalex.org/W3035688398","https://openalex.org/W3094550259","https://openalex.org/W4293846201","https://openalex.org/W6600983433","https://openalex.org/W6739868092","https://openalex.org/W6758684365","https://openalex.org/W6758975236","https://openalex.org/W6760716073","https://openalex.org/W6765694979","https://openalex.org/W6771326840","https://openalex.org/W6771438384","https://openalex.org/W6771809012","https://openalex.org/W6779473860","https://openalex.org/W6955071965"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"As":[0],"audio-visual":[1],"systems":[2],"are":[3,176],"being":[4],"deployed":[5],"for":[6],"safety-critical":[7],"tasks":[8],"such":[9],"as":[10,200,203],"surveillance":[11],"and":[12,108,167],"malicious":[13],"content":[14],"filtering,":[15],"their":[16,182],"robustness":[17,26,74,94,140,157],"remains":[18],"an":[19],"under-studied":[20],"area.":[21],"Existing":[22],"published":[23],"work":[24,42,125],"on":[25,151,164],"either":[27],"does":[28,35],"not":[29,36,177],"scale":[30],"to":[31,44,50,70,80,84,112,154],"large-scale":[32,101],"dataset,":[33],"or":[34],"deal":[37],"with":[38,131],"multiple":[39],"modalities.":[40],"This":[41],"aims":[43],"study":[45],"several":[46],"key":[47],"questions":[48],"related":[49],"multi-modal":[51,60,76,89,97,136,174],"learning":[52],"through":[53,141],"the":[54,73,93,96,115,156,159,186],"lens":[55],"of":[56,75,95,117,158,188],"robustness:":[57],"1)":[58],"Are":[59],"models":[61,175],"necessarily":[62,178],"more":[63,87,179],"robust":[64,88,180],"than":[65,181],"uni-modal":[66,183],"models?":[67],"2)":[68],"How":[69,79],"efficiently":[71,113],"measure":[72,114],"learning?":[77],"3)":[78],"fuse":[81],"different":[82],"modalities":[83],"achieve":[85,199],"a":[86,100,105,109,127,147,208],"model?":[90],"To":[91],"understand":[92],"model":[98],"in":[99,120,185],"setting,":[102],"we":[103],"propose":[104],"density-based":[106],"metric,":[107],"convexity":[110],"metric":[111],"distribution":[116],"each":[118],"modality":[119],"high-dimensional":[121],"latent":[122],"space.":[123],"Our":[124,162],"provides":[126],"theoretical":[128],"intuition":[129],"together":[130],"empirical":[132],"evidence":[133],"showing":[134],"how":[135],"fusion":[137],"affects":[138],"adversarial":[139,189,205],"these":[142],"metrics.":[143],"We":[144,191],"further":[145],"devise":[146],"mix-up":[148,195],"strategy":[149],"based":[150],"our":[152,171,194],"metrics":[153],"improve":[155],"trained":[160,196],"model.":[161],"experiments":[163],"AudioSet":[165],"[1]":[166],"Kinetics-Sounds":[168],"[2]":[169],"verify":[170],"hypothesis":[172],"that":[173],"counterparts":[184],"face":[187],"examples.":[190],"also":[192],"observe":[193],"method":[197],"could":[198],"much":[201],"protection":[202],"traditional":[204],"training,":[206],"offering":[207],"computationally":[209],"cheap":[210],"alternative.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}