{"id":"https://openalex.org/W4415540868","doi":"https://doi.org/10.1145/3746027.3754741","title":"ALDEN: Dual-Level Disentanglement with Meta-learning for Generalizable Audio Deepfake Detection","display_name":"ALDEN: Dual-Level Disentanglement with Meta-learning for Generalizable Audio Deepfake Detection","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540868","doi":"https://doi.org/10.1145/3746027.3754741"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754741","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754741","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","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/A5008799032","display_name":"Yuxiong Xu","orcid":"https://orcid.org/0000-0002-0514-3698"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiong Xu","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-0514-3698","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365163","display_name":"Bin Li","orcid":"https://orcid.org/0000-0002-2613-5451"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Li","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2613-5451","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033791278","display_name":"Weixiang Li","orcid":"https://orcid.org/0000-0001-5094-6548"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weixiang Li","raw_affiliation_strings":["Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5094-6548","affiliations":[{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Intelligent Information Processing, Shenzhen, China, Shenzhen Key Laboratory of Media Security, Shenzhen, China, and Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043644234","display_name":"Sara Mandelli","orcid":"https://orcid.org/0000-0003-3811-003X"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sara Mandelli","raw_affiliation_strings":["Politecnico di Milano, Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB), Milan, Italy"],"raw_orcid":"https://orcid.org/0000-0003-3811-003X","affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB), Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107473146","display_name":"Viola Negroni","orcid":"https://orcid.org/0009-0000-2483-4366"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Viola Negroni","raw_affiliation_strings":["Politecnico di Milano, Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB), Milan, Italy"],"raw_orcid":"https://orcid.org/0009-0000-2483-4366","affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB), Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":null,"display_name":"Sheng Li","orcid":"https://orcid.org/0009-0000-2761-1918"},"institutions":[{"id":"https://openalex.org/I4210089559","display_name":"Shenzhen Metro (China)","ror":"https://ror.org/008hpge95","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210089559"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["Afirstsoft Technology Group Co., Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0000-2761-1918","affiliations":[{"raw_affiliation_string":"Afirstsoft Technology Group Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I4210089559"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.33199331,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7277","last_page":"7286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9979000091552734,"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":0.9979000091552734,"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/T11309","display_name":"Music and Audio Processing","score":0.9940000176429749,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9936000108718872,"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/overfitting","display_name":"Overfitting","score":0.9280999898910522},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.8357999920845032},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.619700014591217},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.328000009059906},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3077999949455261}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9280999898910522},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8357999920845032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8104000091552734},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6370000243186951},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.619700014591217},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4494999945163727},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3540000021457672},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34200000762939453},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3077999949455261},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754741","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754741","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7122122651","display_name":null,"funder_award_id":"U23B2022, U22B2047, and 62202310","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1976526581","https://openalex.org/W2101807845","https://openalex.org/W2163922914","https://openalex.org/W2590129515","https://openalex.org/W2603777577","https://openalex.org/W2963043696","https://openalex.org/W2963300588","https://openalex.org/W2972811785","https://openalex.org/W2990440871","https://openalex.org/W3201397251","https://openalex.org/W3209984917","https://openalex.org/W4210970267","https://openalex.org/W4292957223","https://openalex.org/W4372260053","https://openalex.org/W4381198892","https://openalex.org/W4382202681","https://openalex.org/W4385800847","https://openalex.org/W4387999491","https://openalex.org/W4399618569","https://openalex.org/W4400188193","https://openalex.org/W4400188660","https://openalex.org/W4401582003","https://openalex.org/W4402378055","https://openalex.org/W4403955195","https://openalex.org/W4405182531","https://openalex.org/W4405521770"],"related_works":[],"abstract_inverted_index":{"A":[0],"significant":[1],"challenge":[2],"in":[3,79,127,155],"audio":[4,77],"deepfake":[5],"detection":[6],"(ADD)":[7],"is":[8,134],"to":[9,25,68,136,142],"improve":[10],"model":[11],"generalization":[12,145],"against":[13],"unseen":[14],"vocoders":[15],"and":[16,41,72,91,108,157,163],"other":[17],"unknown":[18],"factors,":[19],"as":[20,89,120,141],"existing":[21],"methods":[22,154],"often":[23],"overfit":[24],"specific":[26],"vocoder":[27],"patterns":[28],"or":[29],"synthetic-irrelevant":[30,86,109],"factors.":[31],"To":[32,84],"overcome":[33],"this":[34],"challenge,":[35],"by":[36],"focusing":[37],"on":[38,169],"vocoder-agnostic":[39,71,112,130],"features":[40,110,113,123],"synthetic":[42],"traces":[43],"for":[44],"generalizable":[45],"ADD,":[46,128],"we":[47,59,94],"propose":[48],"a":[49,97,115,129],"novel":[50],"dual-level":[51],"disentanglement":[52,64,99],"with":[53],"meta-learning":[54,131],"(ALDEN":[55],")":[56],"framework.":[57],"Specifically,":[58],"first":[60],"introduce":[61],"an":[62],"adversarial-training-based":[63],"learning":[65,100],"(ADL)":[66],"module":[67,133],"explicitly":[69],"learn":[70],"vocoder-specific":[73],"features,":[74],"effectively":[75],"disentangling":[76],"signals":[78],"terms":[80],"of":[81,117],"low-level":[82,121],"characteristics.":[83],"suppress":[85],"information,":[87],"such":[88],"semantics":[90],"speaker":[92],"identities,":[93],"simultaneously":[95],"employ":[96],"reconstruction-based":[98],"(RDL)":[101],"module,":[102],"which":[103],"further":[104,143],"disentangles":[105],"both":[106],"synthetic-relevant":[107],"from":[111],"at":[114],"high-level":[116],"semantics.":[118],"Additionally,":[119],"non-semantic":[122],"are":[124],"more":[125],"critical":[126],"(VAML)":[132],"proposed":[135],"simulate":[137],"cross-vocoder":[138,156],"scenarios":[139],"so":[140],"boost":[144],"performance.":[146],"Extensive":[147],"experiments":[148],"demonstrate":[149],"that":[150],"ALDEN":[151],"outperforms":[152],"state-of-the-art":[153],"in-the-wild":[158],"scenarios.":[159],"The":[160],"code,":[161],"model,":[162],"supplementary":[164],"materials":[165],"will":[166],"be":[167],"released":[168],"the":[170],"project":[171],"page:":[172],"https://beyond0814.github.io/ALDEN/.":[173]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}