{"id":"https://openalex.org/W4360993864","doi":"https://doi.org/10.1109/tifs.2023.3262148","title":"AVoiD-DF: Audio-Visual Joint Learning for Detecting Deepfake","display_name":"AVoiD-DF: Audio-Visual Joint Learning for Detecting Deepfake","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4360993864","doi":"https://doi.org/10.1109/tifs.2023.3262148"},"language":"en","primary_location":{"id":"doi:10.1109/tifs.2023.3262148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2023.3262148","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-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/A5101619232","display_name":"Wenyuan Yang","orcid":"https://orcid.org/0000-0003-0046-5994"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenyuan Yang","raw_affiliation_strings":["School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China","School of Cyber Science and Technology, Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Cyber Science and Technology, Shenzhen Campus, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101467238","display_name":"Xiaoyu Zhou","orcid":"https://orcid.org/0009-0000-4131-6093"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Zhou","raw_affiliation_strings":["School of Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"affiliations":[{"raw_affiliation_string":"School of Software Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115053622","display_name":"Zhikai Chen","orcid":"https://orcid.org/0009-0000-5398-2026"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhikai Chen","raw_affiliation_strings":["Zhuque Laboratory, Tencent Security, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Zhuque Laboratory, Tencent Security, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038224522","display_name":"Bofei Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bofei Guo","raw_affiliation_strings":["School of Electronic and Computer Engineering, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072485378","display_name":"Zhongjie Ba","orcid":"https://orcid.org/0000-0003-0921-8869"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongjie Ba","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China","ZJU-Hangzhou Global Scientific and Technological Innovation Center, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"ZJU-Hangzhou Global Scientific and Technological Innovation Center, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005319671","display_name":"Zhihua Xia","orcid":"https://orcid.org/0000-0001-6860-647X"},"institutions":[{"id":"https://openalex.org/I159948400","display_name":"Jinan University","ror":"https://ror.org/02xe5ns62","country_code":"CN","type":"education","lineage":["https://openalex.org/I159948400"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihua Xia","raw_affiliation_strings":["College of Cyber Security, Jinan University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"College of Cyber Security, Jinan University, Guangzhou, China","institution_ids":["https://openalex.org/I159948400"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068837264","display_name":"Xiaochun Cao","orcid":"https://orcid.org/0000-0001-7141-708X"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaochun Cao","raw_affiliation_strings":["School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China","School of Cyber Science and Technology, Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"School of Cyber Science and Technology, Shenzhen Campus, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105297718","display_name":"Kui Ren","orcid":"https://orcid.org/0000-0002-1969-2591"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kui Ren","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University, Hangzhou, China","ZJU-Hangzhou Global Scientific and Technological Innovation Center, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I168879160"]},{"raw_affiliation_string":"ZJU-Hangzhou Global Scientific and Technological Innovation Center, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5101619232"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":17.9747,"has_fulltext":false,"cited_by_count":151,"citation_normalized_percentile":{"value":0.99571986,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"18","issue":null,"first_page":"2015","last_page":"2029"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9998000264167786,"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":0.9998000264167786,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9984999895095825,"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":0.9955999851226807,"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/computer-science","display_name":"Computer science","score":0.8855780363082886},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.7112444639205933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.576029896736145},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5332885384559631},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5031480193138123},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.49321049451828003},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.48354220390319824},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4812997877597809},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.478670209646225},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.45383220911026},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3743731379508972},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35728344321250916}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8855780363082886},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7112444639205933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.576029896736145},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5332885384559631},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5031480193138123},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.49321049451828003},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.48354220390319824},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4812997877597809},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.478670209646225},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45383220911026},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3743731379508972},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35728344321250916},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tifs.2023.3262148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2023.3262148","pdf_url":null,"source":{"id":"https://openalex.org/S61310614","display_name":"IEEE Transactions on Information Forensics and Security","issn_l":"1556-6013","issn":["1556-6013","1556-6021"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Information Forensics and Security","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2051114290","display_name":null,"funder_award_id":"62172359","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2434235226","display_name":null,"funder_award_id":"62261160653","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5790315762","display_name":null,"funder_award_id":"2022YFB3103504","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6258482808","display_name":null,"funder_award_id":"62122032","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7305691841","display_name":null,"funder_award_id":"20220016","funder_id":"https://openalex.org/F4320336569","funder_display_name":"Shenzhen Science and Technology Innovation Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320336569","display_name":"Shenzhen Science and Technology Innovation Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W1482998036","https://openalex.org/W2558151185","https://openalex.org/W2745896134","https://openalex.org/W2891145043","https://openalex.org/W2904573504","https://openalex.org/W2913399670","https://openalex.org/W2936802426","https://openalex.org/W2963150162","https://openalex.org/W2963684180","https://openalex.org/W2964227577","https://openalex.org/W2967606780","https://openalex.org/W2969985801","https://openalex.org/W2972909277","https://openalex.org/W2981523288","https://openalex.org/W2982058372","https://openalex.org/W2990074387","https://openalex.org/W2998405168","https://openalex.org/W3015925607","https://openalex.org/W3024869864","https://openalex.org/W3026777299","https://openalex.org/W3033711348","https://openalex.org/W3034658206","https://openalex.org/W3034713808","https://openalex.org/W3034900344","https://openalex.org/W3036198682","https://openalex.org/W3081492798","https://openalex.org/W3093010840","https://openalex.org/W3093077034","https://openalex.org/W3096084197","https://openalex.org/W3101631197","https://openalex.org/W3110606395","https://openalex.org/W3113824005","https://openalex.org/W3126757411","https://openalex.org/W3128609017","https://openalex.org/W3154326567","https://openalex.org/W3159168402","https://openalex.org/W3160325739","https://openalex.org/W3162322471","https://openalex.org/W3162565403","https://openalex.org/W3169588269","https://openalex.org/W3173581984","https://openalex.org/W3174508664","https://openalex.org/W3174763799","https://openalex.org/W3174831884","https://openalex.org/W3175342695","https://openalex.org/W3176241004","https://openalex.org/W3177027279","https://openalex.org/W3177116139","https://openalex.org/W3186090335","https://openalex.org/W3197358873","https://openalex.org/W3201773091","https://openalex.org/W3207531490","https://openalex.org/W4205415396","https://openalex.org/W4210623456","https://openalex.org/W4214680478","https://openalex.org/W4225352246","https://openalex.org/W4225527248","https://openalex.org/W4287758545","https://openalex.org/W4287777632","https://openalex.org/W4288090950","https://openalex.org/W4312753047","https://openalex.org/W4319978495","https://openalex.org/W4320882980","https://openalex.org/W4385245566","https://openalex.org/W4386928847","https://openalex.org/W6752888775","https://openalex.org/W6757599822","https://openalex.org/W6769705151","https://openalex.org/W6769741248","https://openalex.org/W6777481484","https://openalex.org/W6784810453","https://openalex.org/W6789985038","https://openalex.org/W6790220185","https://openalex.org/W6797657831","https://openalex.org/W6799942944","https://openalex.org/W6801088966","https://openalex.org/W6804185262"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4312814274","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W4301143707","https://openalex.org/W2952745240"],"abstract_inverted_index":{"Recently,":[0],"deepfakes":[1],"have":[2,17],"raised":[3],"severe":[4],"concerns":[5],"about":[6],"the":[7,23,140,160],"authenticity":[8],"of":[9,34,37,139],"online":[10],"media.":[11],"Prior":[12],"works":[13],"for":[14,50,58,104,125],"deepfake":[15,27,105,127,148,166],"detection":[16,106],"made":[18],"many":[19,163],"efforts":[20],"to":[21,78,93],"capture":[22],"intra-modal":[24,99],"artifacts.":[25],"However,":[26],"videos":[28],"in":[29,69,165],"real-world":[30],"scenarios":[31],"often":[32],"consist":[33],"a":[35,88,115,121],"combination":[36],"audio":[38],"and":[39,82,98,112,156],"visual.":[40],"In":[41],"this":[42],"paper,":[43],"we":[44,119],"propose":[45],"an":[46],"Audio-Visual":[47],"Joint":[48],"Learning":[49],"Detecting":[51],"Deepfake":[52],"(AVoiD-DF),":[53],"which":[54],"exploits":[55],"audio-visual":[56],"inconsistency":[57],"multi-modal":[59,80,126],"forgery":[60,117,177],"detection.":[61,128,167],"Specifically,":[62],"AVoiD-DF":[63,161],"begins":[64],"by":[65,146],"embedding":[66],"temporal-spatial":[67],"information":[68],"Temporal-Spatial":[70],"Encoder.":[71],"A":[72],"Multi-Modal":[73],"Joint-Decoder":[74],"is":[75,91],"then":[76],"designed":[77],"fuse":[79],"features":[81],"jointly":[83],"learn":[84],"inherent":[85],"relationships.":[86],"Afterward,":[87],"Cross-Modal":[89],"Classifier":[90],"devised":[92],"detect":[94],"manipulation":[95],"with":[96,133],"inter-modal":[97],"disharmony.":[100],"Since":[101],"existing":[102],"datasets":[103],"mainly":[107],"focus":[108],"on":[109,153,175],"one":[110,138],"modality":[111],"only":[113],"cover":[114],"few":[116],"methods,":[118],"build":[120],"novel":[122],"benchmark":[123],"DefakeAVMiT":[124,129],"contains":[130],"sufficient":[131],"visuals":[132],"corresponding":[134],"audios,":[135],"where":[136],"any":[137],"modalities":[141],"may":[142],"be":[143],"maliciously":[144],"modified":[145],"multiple":[147],"methods.":[149],"The":[150],"experimental":[151],"results":[152],"DefakeAVMiT,":[154],"FakeAVCeleb,":[155],"DFDC":[157],"demonstrate":[158],"that":[159],"outperforms":[162],"state-of-the-arts":[164],"Our":[168],"proposed":[169],"method":[170],"also":[171],"yields":[172],"superior":[173],"generalization":[174],"various":[176],"techniques.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":79},{"year":2024,"cited_by_count":43},{"year":2023,"cited_by_count":19}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}