{"id":"https://openalex.org/W4403791323","doi":"https://doi.org/10.1145/3664647.3680795","title":"AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset","display_name":"AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403791323","doi":"https://doi.org/10.1145/3664647.3680795"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680795","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680795","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 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3664647.3680795","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044104932","display_name":"Zhixi Cai","orcid":"https://orcid.org/0000-0001-7978-0860"},"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":true,"raw_author_name":"Zhixi Cai","raw_affiliation_strings":["Monash University, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7978-0860","affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034501904","display_name":"Shreya Ghosh","orcid":"https://orcid.org/0000-0002-2639-8374"},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Shreya Ghosh","raw_affiliation_strings":["Curtin University, Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2639-8374","affiliations":[{"raw_affiliation_string":"Curtin University, Perth, Australia","institution_ids":["https://openalex.org/I205640436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111082337","display_name":"Aman Pankaj Adatia","orcid":"https://orcid.org/0009-0007-9585-404X"},"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":"Aman Pankaj Adatia","raw_affiliation_strings":["Indian Institute of Technology Ropar, Ropar, India"],"raw_orcid":"https://orcid.org/0009-0007-9585-404X","affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Ropar, Ropar, India","institution_ids":["https://openalex.org/I119241673"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041437150","display_name":"Munawar Hayat","orcid":"https://orcid.org/0000-0002-2706-5985"},"institutions":[{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Munawar Hayat","raw_affiliation_strings":["Qualcomm, San Diego, USA"],"raw_orcid":"https://orcid.org/0000-0002-2706-5985","affiliations":[{"raw_affiliation_string":"Qualcomm, San Diego, USA","institution_ids":["https://openalex.org/I4210087596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085376429","display_name":"Abhinav Dhall","orcid":"https://orcid.org/0000-0002-2230-1440"},"institutions":[{"id":"https://openalex.org/I169541294","display_name":"Flinders University","ror":"https://ror.org/01kpzv902","country_code":"AU","type":"education","lineage":["https://openalex.org/I169541294"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Abhinav Dhall","raw_affiliation_strings":["Flinders University, Adelaide, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2230-1440","affiliations":[{"raw_affiliation_string":"Flinders University, Adelaide, Australia","institution_ids":["https://openalex.org/I169541294"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030379402","display_name":"Tom Gedeon","orcid":"https://orcid.org/0000-0001-8356-4909"},"institutions":[{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tom Gedeon","raw_affiliation_strings":["Curtin University of Technology, Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8356-4909","affiliations":[{"raw_affiliation_string":"Curtin University of Technology, Perth, Australia","institution_ids":["https://openalex.org/I205640436"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081566320","display_name":"Kalin Stefanov","orcid":"https://orcid.org/0000-0002-0861-8660"},"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":"Kalin Stefanov","raw_affiliation_strings":["Monash University, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0002-0861-8660","affiliations":[{"raw_affiliation_string":"Monash University, Melbourne, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5044104932"],"corresponding_institution_ids":["https://openalex.org/I56590836"],"apc_list":null,"apc_paid":null,"fwci":12.4113,"has_fulltext":true,"cited_by_count":39,"citation_normalized_percentile":{"value":0.9928871,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7414","last_page":"7423"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9972000122070312,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7527738809585571},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.675126314163208},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.6596351861953735},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36705225706100464},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3217446506023407},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.26020216941833496},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.07509219646453857},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.052323490381240845}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7527738809585571},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.675126314163208},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.6596351861953735},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36705225706100464},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3217446506023407},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.26020216941833496},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07509219646453857},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.052323490381240845}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3680795","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680795","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 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:monash.edu:publications/69058092-437b-4194-9404-995f96cd0c1e","is_oa":true,"landing_page_url":"https://research.monash.edu/en/publications/69058092-437b-4194-9404-995f96cd0c1e","pdf_url":"https://researchmgt.monash.edu/ws/files/668653929/640947208-oa.pdf","source":{"id":"https://openalex.org/S4306402625","display_name":"Monash University Research Portal (Monash University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I56590836","host_organization_name":"Monash University","host_organization_lineage":["https://openalex.org/I56590836"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Cai, Z, Ghosh, S, Adatia, A P, Hayat, M, Dhall, A, Gedeon, T & Stefanov, K 2024, AV-Deepfake1M : A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset. in Y Luo, T Do & Y Yan (eds), MM 2024 - Proceedings of the 32nd ACM International Conference on Multimedia. Association for Computing Machinery (ACM), New York NY USA, pp. 7414-7423, ACM International Conference on Multimedia 2024, Melbourne, Victoria, Australia, 28/10/24. https://doi.org/10.1145/3664647.3680795","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1145/3664647.3680795","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3664647.3680795","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 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W46948191","https://openalex.org/W2133665775","https://openalex.org/W2531409750","https://openalex.org/W2612690371","https://openalex.org/W2808631503","https://openalex.org/W2891145043","https://openalex.org/W2944294033","https://openalex.org/W2964216549","https://openalex.org/W2972478942","https://openalex.org/W2982058372","https://openalex.org/W3034196597","https://openalex.org/W3034713808","https://openalex.org/W3034900344","https://openalex.org/W3092879151","https://openalex.org/W3093010840","https://openalex.org/W3093077034","https://openalex.org/W3154326567","https://openalex.org/W3175342695","https://openalex.org/W3178572954","https://openalex.org/W3178708968","https://openalex.org/W3211147706","https://openalex.org/W4200411312","https://openalex.org/W4212774754","https://openalex.org/W4214684483","https://openalex.org/W4281730245","https://openalex.org/W4287958448","https://openalex.org/W4312388562","https://openalex.org/W4360993864","https://openalex.org/W4372260310","https://openalex.org/W4381198892","https://openalex.org/W4385822353","https://openalex.org/W4386057769","https://openalex.org/W4386065999","https://openalex.org/W4386075487","https://openalex.org/W4386076085","https://openalex.org/W4386076380","https://openalex.org/W4386076638","https://openalex.org/W4386076652","https://openalex.org/W4386102876","https://openalex.org/W4386272941","https://openalex.org/W4389519587","https://openalex.org/W4390873135","https://openalex.org/W4391952560","https://openalex.org/W4402774452","https://openalex.org/W6601908271"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2271369634","https://openalex.org/W3147472394","https://openalex.org/W2047100085","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W3137890128"],"abstract_inverted_index":{"The":[0,73,101,125,149,164],"detection":[1,135],"and":[2,35,68,83,136,166],"localization":[3,46,137,162],"of":[4,21,44,47,50,64,96,107,118,121,128],"highly":[5],"realistic":[6],"deepfake":[7,33,134,161],"audio-visual":[8,51,85],"content":[9,66],"are":[10,28,169],"challenging":[11],"even":[12],"for":[13,87],"the":[14,22,42,45,62,70,108,119,122,129,159],"most":[15,20],"advanced":[16],"state-of-the-art":[17,133],"methods.":[18,163],"While":[19],"research":[23],"efforts":[24],"in":[25,54,93,143,157],"this":[26,58],"domain":[27],"focused":[29],"on":[30],"detecting":[31],"high-quality":[32],"images":[34],"videos,":[36],"only":[37],"a":[38,94,104,115,140,154],"few":[39],"works":[40],"address":[41],"problem":[43],"small":[48],"segments":[49],"manipulations":[52,86],"embedded":[53],"real":[55],"videos.":[56,100],"In":[57],"research,":[59],"we":[60],"emulate":[61],"process":[63],"such":[65],"generation":[67,111],"propose":[69],"AV-Deepfake1M":[71],"dataset.":[72],"dataset":[74,131,151,165],"contains":[75],"content-driven":[76],"(i)":[77],"video":[78],"manipulations,":[79,82],"(ii)":[80],"audio":[81],"(iii)":[84],"more":[88,97],"than":[89,98],"2K":[90],"subjects":[91],"resulting":[92],"total":[95],"1M":[99],"paper":[102],"provides":[103],"thorough":[105],"description":[106],"proposed":[109,130,150],"data":[110],"pipeline":[112],"accompanied":[113],"by":[114],"rigorous":[116],"analysis":[117],"quality":[120],"generated":[123],"data.":[124],"comprehensive":[126],"benchmark":[127],"utilizing":[132],"methods":[138],"indicates":[139],"significant":[141],"drop":[142],"performance":[144],"compared":[145],"to":[146],"previous":[147],"datasets.":[148],"will":[152],"play":[153],"vital":[155],"role":[156],"building":[158],"next-generation":[160],"associated":[167],"code":[168],"available":[170],"at":[171],"https://github.com/ControlNet/AV-Deepfake1M.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-14T08:36:36.166977","created_date":"2025-10-10T00:00:00"}