{"id":"https://openalex.org/W7108716326","doi":"https://doi.org/10.5281/zenodo.17811489","title":"MAIA: An Inpainting-Based Approach for Music Adversarial Attacks","display_name":"MAIA: An Inpainting-Based Approach for Music Adversarial Attacks","publication_year":2025,"publication_date":"2025-09-21","ids":{"openalex":"https://openalex.org/W7108716326","doi":"https://doi.org/10.5281/zenodo.17811489"},"language":null,"primary_location":{"id":"doi:10.5281/zenodo.17811489","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811489","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.17811489","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yuxuan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxuan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Peihong Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peihong Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Rui Sang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Sang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhixin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhixin Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Shengchen Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengchen Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.54078107,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.4927000105381012,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.4927000105381012,"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":0.2662999927997589,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.04769999906420708,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.9496999979019165},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.5162000060081482},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.49239999055862427},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.48100000619888306},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.41670000553131104},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3799999952316284},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.3723999857902527}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9496999979019165},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5819000005722046},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.5162000060081482},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.49239999055862427},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.48100000619888306},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.44920000433921814},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.41670000553131104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3382999897003174},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C65856478","wikidata":"https://www.wikidata.org/wiki/Q3991682","display_name":"Attack model","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C11560541","wikidata":"https://www.wikidata.org/wiki/Q1756025","display_name":"Replay attack","level":3,"score":0.2680000066757202},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.25929999351501465},{"id":"https://openalex.org/C140547941","wikidata":"https://www.wikidata.org/wiki/Q7797194","display_name":"Threat model","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C2988773926","wikidata":"https://www.wikidata.org/wiki/Q25104379","display_name":"Generative adversarial network","level":3,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.17811489","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811489","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"ConferencePaper"}],"best_oa_location":{"id":"doi:10.5281/zenodo.17811489","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.17811489","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"ConferencePaper"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.44202661514282227}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Music":[0,11,20],"adversarial":[1,27,76,112],"attacks":[2],"have":[3],"garnered":[4],"significant":[5],"interest":[6],"in":[7,90,118],"the":[8,66,69,106,111,124],"field":[9],"of":[10,68,110],"Information":[12],"Retrieval":[13],"(MIR).":[14],"In":[15],"this":[16],"paper,":[17],"we":[18],"present":[19],"Adversarial":[21],"Inpainting":[22],"Attack":[23],"(MAIA),":[24],"a":[25],"novel":[26],"attack":[28,36,87],"framework":[29],"that":[30],"supports":[31],"both":[32,91],"white-box":[33,94],"and":[34,74,93,122,129],"black-box":[35,92],"scenarios.":[37],"MAIA":[38,80],"begins":[39],"with":[40,63],"an":[41],"importance":[42],"analysis":[43],"to":[44],"identify":[45],"critical":[46],"audio":[47,108],"segments,":[48],"which":[49],"are":[50,61],"then":[51],"targeted":[52],"for":[53,126],"modification.":[54],"Utilizing":[55],"generative":[56],"inpainting":[57],"models,":[58],"these":[59],"segments":[60],"reconstructed":[62],"guidance":[64],"from":[65],"output":[67],"attacked":[70],"model,":[71],"ensuring":[72],"subtle":[73],"effective":[75],"perturbations.":[77],"We":[78],"evaluate":[79],"on":[81],"multiple":[82],"MIR":[83,120],"tasks,":[84],"demonstrating":[85],"high":[86,107],"success":[88],"rates":[89],"settings":[95],"while":[96],"maintaining":[97],"minimal":[98],"perceptual":[99],"distortion.":[100],"Additionally,":[101],"subjective":[102],"listening":[103],"tests":[104],"confirm":[105],"fidelity":[109],"samples.":[113],"Our":[114],"findings":[115],"highlight":[116],"vulnerabilities":[117],"current":[119],"systems":[121],"emphasize":[123],"need":[125],"more":[127],"robust":[128],"secure":[130],"models.":[131]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-12-05T00:00:00"}