{"id":"https://openalex.org/W4387968133","doi":"https://doi.org/10.1145/3581783.3612475","title":"Cross-modal and Cross-medium Adversarial Attack for Audio","display_name":"Cross-modal and Cross-medium Adversarial Attack for Audio","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968133","doi":"https://doi.org/10.1145/3581783.3612475"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612475","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5032181314","display_name":"Liguo Zhang","orcid":"https://orcid.org/0000-0002-3814-7783"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liguo Zhang","raw_affiliation_strings":["Harbin Engineering University, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060062358","display_name":"Zilin Tian","orcid":"https://orcid.org/0009-0001-6401-6314"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zilin Tian","raw_affiliation_strings":["Harbin Engineering University, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050857799","display_name":"Yunfei Long","orcid":"https://orcid.org/0009-0009-1458-4514"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunfei Long","raw_affiliation_strings":["Harbin Engineering University, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028477248","display_name":"Sizhao Li","orcid":"https://orcid.org/0000-0002-6557-262X"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sizhao Li","raw_affiliation_strings":["Harbin Engineering University, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101771010","display_name":"Guisheng Yin","orcid":"https://orcid.org/0000-0003-0924-4741"},"institutions":[{"id":"https://openalex.org/I151727225","display_name":"Harbin Engineering University","ror":"https://ror.org/03x80pn82","country_code":"CN","type":"education","lineage":["https://openalex.org/I151727225"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guisheng Yin","raw_affiliation_strings":["Harbin Engineering University, Harbin, China"],"affiliations":[{"raw_affiliation_string":"Harbin Engineering University, Harbin, China","institution_ids":["https://openalex.org/I151727225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5032181314"],"corresponding_institution_ids":["https://openalex.org/I151727225"],"apc_list":null,"apc_paid":null,"fwci":0.1204,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42956899,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"444","last_page":"453"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9972000122070312,"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":0.9972000122070312,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9902999997138977,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9883000254631042,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.772163450717926},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7090102434158325},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6703282594680786},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5513947010040283},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4355999827384949},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4103032648563385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.395415723323822},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3868025839328766},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.15914210677146912},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10756069421768188}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.772163450717926},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7090102434158325},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6703282594680786},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5513947010040283},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4355999827384949},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4103032648563385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.395415723323822},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3868025839328766},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.15914210677146912},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10756069421768188},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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:10.1145/3581783.3612475","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life below water","id":"https://metadata.un.org/sdg/14","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2038484192","https://openalex.org/W2120847449","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2293768274","https://openalex.org/W2359377300","https://openalex.org/W2466903746","https://openalex.org/W2746600820","https://openalex.org/W2811482466","https://openalex.org/W2954420970","https://openalex.org/W2962747881","https://openalex.org/W2963446712","https://openalex.org/W2963857521","https://openalex.org/W3015625436","https://openalex.org/W3017720918","https://openalex.org/W3022863654","https://openalex.org/W3034429256","https://openalex.org/W3034892461","https://openalex.org/W3084156817","https://openalex.org/W3085356816","https://openalex.org/W3091508658","https://openalex.org/W3091896612","https://openalex.org/W3106412272","https://openalex.org/W3110891924","https://openalex.org/W3129419153","https://openalex.org/W3132949086","https://openalex.org/W3138598836","https://openalex.org/W3158291757","https://openalex.org/W3162646160","https://openalex.org/W3167369733","https://openalex.org/W3185321995","https://openalex.org/W3202129910","https://openalex.org/W3205672068","https://openalex.org/W3206285027","https://openalex.org/W3206456554","https://openalex.org/W3207416200","https://openalex.org/W4224950673","https://openalex.org/W4285094241","https://openalex.org/W4300824008","https://openalex.org/W4309613630","https://openalex.org/W4313443012","https://openalex.org/W4313855655","https://openalex.org/W4319862670"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2897924318","https://openalex.org/W2138997758","https://openalex.org/W4360764600"],"abstract_inverted_index":{"Acoustic":[0],"waves":[1,200],"are":[2,28],"forms":[3],"of":[4,92,161,215],"energy":[5],"that":[6,87,107,189,203,221],"propagate":[7],"through":[8],"various":[9],"mediums.":[10],"They":[11],"can":[12,192,222],"be":[13],"represented":[14],"by":[15,143],"different":[16,117],"modalities,":[17],"such":[18],"as":[19,31],"auditory":[20],"signals":[21,69,228],"and":[22,38,56,122,128,184,201,232,240],"visual":[23],"patterns.":[24],"The":[25,176,234],"two":[26],"modalities":[27,118],"often":[29],"described":[30],"one-dimensional":[32],"waveform":[33,102],"in":[34,41,111,230],"the":[35,42,71,78,89,98,108,112,116,151,159,162,205,212],"time":[36],"domain":[37],"two-dimensional":[39],"spectrogram":[40,163],"frequency":[43],"domain.":[44],"Most":[45],"acoustic":[46,227],"signal":[47],"processing":[48,224],"methods":[49,86],"use":[50],"single":[51],"modal":[52],"data":[53,109],"for":[54,63,171,198,226],"input":[55,72],"training":[57],"models.":[58,175],"This":[59,95],"poses":[60],"a":[61,124],"challenge":[62],"black-box":[64,172],"adversarial":[65,93,130,169,218],"attacks":[66,194],"on":[67,195],"audio":[68,173,207],"because":[70],"modality":[73],"is":[74,178],"also":[75],"unknown":[76],"to":[77,103,153,180,243],"attacker.":[79],"In":[80],"fact,":[81],"there":[82],"currently":[83],"exist":[84],"no":[85],"explore":[88,211],"cross-modal":[90,99,127,140],"transferability":[91,100],"perturbation.":[94],"paper":[96],"investigates":[97],"from":[101],"spectrogram.":[104],"We":[105],"argue":[106],"distributions":[110],"sample":[113,164],"space":[114,165],"with":[115,139],"have":[119],"mapping":[120],"relations":[121],"propose":[123],"novel":[125],"decision-based":[126],"cross-medium":[129,213],"attack":[131,141,219],"method.":[132],"Specifically,":[133],"it":[134],"generates":[135],"an":[136],"initial":[137],"example":[138],"capability":[142,214],"combining":[144],"random":[145],"natural":[146],"noise,":[147],"then":[148],"iteratively":[149,167],"reduces":[150],"perturbation":[152,177],"enhance":[154],"its":[155],"invisibility.":[156],"It":[157],"incorporates":[158],"constraints":[160],"while":[166],"optimizing":[168],"perturbations":[170],"classification":[174,196],"imperceptible":[179],"humans,":[181],"both":[182],"visually":[183],"aurally.":[185],"Extensive":[186],"experiments":[187],"demonstrate":[188],"our":[190,216],"approach":[191],"launch":[193],"models":[197,225],"sound":[199],"spectrograms":[202],"share":[204],"same":[206],"signal.":[208],"Furthermore,":[209],"we":[210],"proposed":[217,235],"strategy":[220],"target":[223],"propagating":[229],"air":[231],"seawater.":[233],"method":[236],"has":[237],"preeminent":[238],"invisibility":[239],"generalization":[241],"compared":[242],"other":[244],"methods.":[245]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}