{"id":"https://openalex.org/W7133352136","doi":"https://doi.org/10.1109/ijcb65343.2025.11410761","title":"Investigating the Viability of Employing Multi-modal Large Language Models in the Context of Audio Deepfake Detection","display_name":"Investigating the Viability of Employing Multi-modal Large Language Models in the Context of Audio Deepfake Detection","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W7133352136","doi":"https://doi.org/10.1109/ijcb65343.2025.11410761"},"language":null,"primary_location":{"id":"doi:10.1109/ijcb65343.2025.11410761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcb65343.2025.11410761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Joint Conference on Biometrics (IJCB)","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/A5092300577","display_name":"Akanksha Chuchra","orcid":"https://orcid.org/0000-0003-1041-9350"},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Akanksha Chuchra","raw_affiliation_strings":["Indian Institute of Technology,Ropar,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Ropar,India","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104348030","display_name":"Shukesh Reddy","orcid":null},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shukesh Reddy","raw_affiliation_strings":["Birla Institute of Technology and Science,Machine Intelligence Group,Pilani,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Birla Institute of Technology and Science,Machine Intelligence Group,Pilani,India","institution_ids":["https://openalex.org/I74796645"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055393595","display_name":"Sudeepta Mishra","orcid":"https://orcid.org/0000-0003-4821-4318"},"institutions":[{"id":"https://openalex.org/I119241673","display_name":"Indian Institute of Technology Ropar","ror":"https://ror.org/02qkhhn56","country_code":"IN","type":"education","lineage":["https://openalex.org/I119241673"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sudeepta Mishra","raw_affiliation_strings":["Indian Institute of Technology,Ropar,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology,Ropar,India","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025520963","display_name":"Abhijit Das","orcid":"https://orcid.org/0000-0002-6793-0582"},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abhijit Das","raw_affiliation_strings":["Birla Institute of Technology and Science,Machine Intelligence Group,Pilani,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Birla Institute of Technology and Science,Machine Intelligence Group,Pilani,India","institution_ids":["https://openalex.org/I74796645"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085376429","display_name":"Abhinav Dhall","orcid":"https://orcid.org/0000-0002-2230-1440"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Abhinav Dhall","raw_affiliation_strings":["Monash University,Melbourne,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University,Melbourne,Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":0.82412598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.15809999406337738,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.15809999406337738,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.07249999791383743,"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/T10860","display_name":"Speech and Audio Processing","score":0.03750000149011612,"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/modalities","display_name":"Modalities","score":0.6815000176429749},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5849999785423279},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.45339998602867126},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3919000029563904},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.3237000107765198},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.28299999237060547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8144000172615051},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.6815000176429749},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5849999785423279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5181000232696533},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.45339998602867126},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4293000102043152},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.361299991607666},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.3237000107765198},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcb65343.2025.11410761","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcb65343.2025.11410761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Joint Conference on Biometrics (IJCB)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7734227180480957,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W2034329102","https://openalex.org/W2531409750","https://openalex.org/W2963460857","https://openalex.org/W3026777299","https://openalex.org/W3163596559","https://openalex.org/W3200167423","https://openalex.org/W3201773091","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W4221138880","https://openalex.org/W4297841787","https://openalex.org/W4312933868","https://openalex.org/W4313547876","https://openalex.org/W4375869126","https://openalex.org/W4385823150","https://openalex.org/W4389519587","https://openalex.org/W4389524500","https://openalex.org/W4391021627","https://openalex.org/W4392172801","https://openalex.org/W4392240262","https://openalex.org/W4392902623","https://openalex.org/W4392902647","https://openalex.org/W4392902854","https://openalex.org/W4392903956","https://openalex.org/W4393178509","https://openalex.org/W4393857491","https://openalex.org/W4401042610","https://openalex.org/W4402112008","https://openalex.org/W4402112110","https://openalex.org/W4402112111","https://openalex.org/W4402670135","https://openalex.org/W4402684170","https://openalex.org/W4402917263","https://openalex.org/W4404765990","https://openalex.org/W4408144899","https://openalex.org/W4408354236","https://openalex.org/W4408799803","https://openalex.org/W4409487087","https://openalex.org/W4411217876","https://openalex.org/W4416036636","https://openalex.org/W7133231369"],"related_works":[],"abstract_inverted_index":{"While":[0],"Vision-Language":[1],"Models":[2,8],"(VLMs)":[3],"and":[4,17,78,100,117,125,159],"Multimodal":[5],"Large":[6],"Language":[7],"(MLLMs)":[9],"have":[10],"shown":[11],"strong":[12],"generalisation":[13],"in":[14,95,119],"detecting":[15],"image":[16],"video":[18],"deepfakes,":[19],"their":[20],"use":[21],"for":[22,40,68,105,144,180],"audio":[23,41,45,69,106,133,145,181],"deepfake":[24,42,70,107,146,182],"detection":[25],"remains":[26],"largely":[27],"unexplored.":[28],"In":[29],"this":[30],"work,":[31],"we":[32,73],"aim":[33],"to":[34,55,62,75,161,163],"explore":[35,76],"the":[36,58,111,152],"potential":[37,179],"of":[38,50,60,113],"MLLMs":[39,61],"detection.":[43,71,108,147,183],"Combining":[44],"inputs":[46],"with":[47,83,134,174],"a":[48,90,135,140],"range":[49],"text":[51],"prompts":[52,82],"as":[53],"queries":[54],"find":[56],"out":[57],"viability":[59],"learn":[63],"robust":[64,102],"representations":[65],"across":[66],"modalities":[67],"Therefore,":[72],"attempt":[74],"text-aware":[77],"context-rich,":[79],"question-answer":[80],"based":[81],"binary":[84],"decisions.":[85],"We":[86,109],"hypothesise":[87],"that":[88,131,151],"such":[89],"feature-guided":[91],"reasoning":[92],"will":[93],"help":[94],"facilitating":[96],"deeper":[97],"multimodal":[98],"understanding":[99],"enable":[101],"feature":[103],"learning":[104],"evaluate":[110],"performance":[112,170],"two":[114,120],"MLLMs,":[115],"Qwen2-Audio-7B-Instruct":[116],"SALMONN,":[118],"evaluation":[121],"modes:":[122],"(a)":[123],"zero-shot":[124],"(b)":[126],"fine-tuned.":[127],"Our":[128,148],"experiments":[129,149],"demonstrate":[130],"combining":[132],"multi-prompt":[136],"approach":[137],"could":[138],"be":[139],"viable":[141],"way":[142],"forward":[143],"show":[150],"models":[153],"perform":[154],"poorly":[155],"without":[156],"task-specific":[157],"training":[158],"struggle":[160],"generalise":[162],"out-of-domain":[164],"data.":[165],"However,":[166],"they":[167],"achieve":[168],"good":[169],"on":[171],"in-domain":[172],"data":[173],"minimal":[175],"supervision,":[176],"indicating":[177],"promising":[178]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-04T00:00:00"}
