{"id":"https://openalex.org/W4415538660","doi":"https://doi.org/10.1145/3746027.3755851","title":"ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake Detection","display_name":"ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake Detection","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538660","doi":"https://doi.org/10.1145/3746027.3755851"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755851","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755851","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755851","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101361643","display_name":"Hao Gu","orcid":"https://orcid.org/0009-0006-6044-8239"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Gu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-6044-8239","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078525423","display_name":"Jiangyan Yi","orcid":"https://orcid.org/0000-0003-2422-4618"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangyan Yi","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2422-4618","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088651555","display_name":"C. F. Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I82760581","display_name":"Taizhou University","ror":"https://ror.org/04fzhyx73","country_code":"CN","type":"education","lineage":["https://openalex.org/I82760581"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Wang","raw_affiliation_strings":["Taizhou University, Taizhou, China"],"raw_orcid":"https://orcid.org/0009-0005-3233-0586","affiliations":[{"raw_affiliation_string":"Taizhou University, Taizhou, China","institution_ids":["https://openalex.org/I82760581"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9344-6428","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001973434","display_name":"Zheng Lian","orcid":"https://orcid.org/0000-0001-9477-0599"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Lian","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9477-0599","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001846517","display_name":"Jiayi He","orcid":"https://orcid.org/0009-0001-1461-5714"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi He","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-1461-5714","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109525927","display_name":"Yong Ren","orcid":"https://orcid.org/0009-0000-9015-000X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Ren","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-9015-000X","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yujie Chen","orcid":"https://orcid.org/0009-0008-4252-8862"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujie Chen","raw_affiliation_strings":["Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0008-4252-8862","affiliations":[{"raw_affiliation_string":"Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111856667","display_name":"Zhengqi Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengqi Wen","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-1632-4293","affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11736","last_page":"11745"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"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/T10860","display_name":"Speech and Audio Processing","score":0.9937000274658203,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7781000137329102},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5339000225067139},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.41200000047683716},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4032000005245209},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.3968000113964081},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3799999952316284}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8296999931335449},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7781000137329102},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5339000225067139},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.41200000047683716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4106000065803528},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4032000005245209},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.3968000113964081},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3799999952316284},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36010000109672546},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3504999876022339},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32659998536109924},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.311599999666214},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3091999888420105},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.305400013923645},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.29660001397132874},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755851","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755851","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":{"id":"doi:10.1145/3746027.3755851","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755851","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6954097034","display_name":null,"funder_award_id":"No. 62322120, No.U21B2010, No. 62306316, No. 62206278, No. 62201572","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":38,"referenced_works":["https://openalex.org/W2963460857","https://openalex.org/W2964052309","https://openalex.org/W3026777299","https://openalex.org/W3096084197","https://openalex.org/W3128666957","https://openalex.org/W3160614129","https://openalex.org/W3163596559","https://openalex.org/W3209059054","https://openalex.org/W3212117663","https://openalex.org/W4221138880","https://openalex.org/W4225527248","https://openalex.org/W4297841787","https://openalex.org/W4322718191","https://openalex.org/W4375869126","https://openalex.org/W4386302282","https://openalex.org/W4388718054","https://openalex.org/W4389519587","https://openalex.org/W4389524500","https://openalex.org/W4392902647","https://openalex.org/W4392903956","https://openalex.org/W4393178509","https://openalex.org/W4394019163","https://openalex.org/W4395064829","https://openalex.org/W4399554060","https://openalex.org/W4402502185","https://openalex.org/W4402701389","https://openalex.org/W4402917263","https://openalex.org/W4403570063","https://openalex.org/W4403748155","https://openalex.org/W4403791925","https://openalex.org/W4403792468","https://openalex.org/W4404344599","https://openalex.org/W4404822886","https://openalex.org/W4404999094","https://openalex.org/W4407719537","https://openalex.org/W4407794264","https://openalex.org/W4413156425","https://openalex.org/W6967192140"],"related_works":[],"abstract_inverted_index":{"Audio":[0],"deepfake":[1],"detection":[2],"(ADD)":[3],"has":[4],"grown":[5],"increasingly":[6],"important":[7],"due":[8],"to":[9,46,105,109,120,152,155],"the":[10,89,92,107,111,149],"rise":[11],"of":[12,59,113],"high-fidelity":[13],"audio":[14,24,35,84,96,132],"generative":[15],"models":[16,27],"and":[17],"their":[18,64],"potential":[19],"for":[20,75],"misuse.":[21],"Given":[22],"that":[23,122,144],"large":[25],"language":[26],"(ALLMs)":[28],"have":[29],"made":[30],"significant":[31],"progress":[32],"in":[33,130,135],"various":[34],"processing":[36],"tasks,":[37],"a":[38,55,139],"heuristic":[39],"question":[40,85],"arises:":[41],"Can":[42],"ALLMs":[43,60,154],"be":[44],"leveraged":[45],"solve":[47],"ADD?.":[48],"In":[49],"this":[50,67,95,145],"paper,":[51],"we":[52,69,78,142],"first":[53],"conduct":[54],"comprehensive":[56],"zero-shot":[57],"evaluation":[58],"on":[61],"ADD,":[62],"revealing":[63],"ineffectiveness.":[65],"To":[66],"end,":[68],"propose":[70],"ALLM4ADD,":[71],"an":[72,83],"ALLM-driven":[73],"framework":[74],"ADD.":[76],"Specifically,":[77],"reformulate":[79],"ADD":[80,159],"task":[81],"as":[82],"answering":[86],"problem,":[87],"prompting":[88],"model":[90],"with":[91],"question:":[93],"''Is":[94],"fake":[97,131],"or":[98],"real?''.":[99],"We":[100],"then":[101],"perform":[102],"supervised":[103],"fine-tuning":[104],"enable":[106],"ALLM":[108],"assess":[110],"authenticity":[112],"query":[114],"audio.":[115],"Extensive":[116],"experiments":[117],"are":[118],"conducted":[119],"demonstrate":[121],"our":[123],"ALLM-based":[124],"method":[125],"can":[126],"achieve":[127],"superior":[128],"performance":[129],"detection,":[133],"particularly":[134],"data-scarce":[136],"scenarios.":[137],"As":[138],"pioneering":[140],"study,":[141],"anticipate":[143],"work":[146],"will":[147],"inspire":[148],"research":[150],"community":[151],"leverage":[153],"develop":[156],"more":[157],"effective":[158],"systems.":[160],"Code":[161],"is":[162],"available":[163],"at":[164],"https://github.com/ucas-hao/qwen_audio_for_add.git.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}