{"id":"https://openalex.org/W4401980784","doi":"https://doi.org/10.1109/tifs.2024.3451356","title":"Using Graph Neural Networks to Improve Generalization Capability of the Models for Deepfake Detection","display_name":"Using Graph Neural Networks to Improve Generalization Capability of the Models for Deepfake Detection","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4401980784","doi":"https://doi.org/10.1109/tifs.2024.3451356"},"language":"en","primary_location":{"id":"doi:10.1109/tifs.2024.3451356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2024.3451356","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":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/Using_Graph_Neural_Networks_to_Improve_Generalization_Capability_of_the_Models_for_Deepfake_Detection/27147699","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025383512","display_name":"Huimin She","orcid":"https://orcid.org/0009-0003-1351-959X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huimin She","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-1351-959X","affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102772000","display_name":"Yongjian Hu","orcid":"https://orcid.org/0000-0002-7775-3786"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongjian Hu","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7775-3786","affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031732848","display_name":"Beibei Liu","orcid":"https://orcid.org/0000-0002-3907-773X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Beibei Liu","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-3907-773X","affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100653936","display_name":"Jicheng Li","orcid":"https://orcid.org/0000-0001-5000-1069"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jicheng Li","raw_affiliation_strings":["School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-5000-1069","affiliations":[{"raw_affiliation_string":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075200053","display_name":"Chang\u2010Tsun Li","orcid":"https://orcid.org/0000-0003-4735-6138"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chang-Tsun Li","raw_affiliation_strings":["School of Information Technology, Deakin University, Geelong, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0003-4735-6138","affiliations":[{"raw_affiliation_string":"School of Information Technology, Deakin University, Geelong, VIC, Australia","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.6727,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.9537619,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"19","issue":null,"first_page":"8414","last_page":"8427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9577999711036682,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9577999711036682,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9417999982833862,"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":0.8631349802017212},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6976891756057739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5165345072746277},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5127916932106018},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48485076427459717},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4755147099494934},{"id":"https://openalex.org/keywords/graph-theory","display_name":"Graph theory","score":0.43557676672935486},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38132262229919434},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3538125157356262},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07997837662696838}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8631349802017212},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6976891756057739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5165345072746277},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5127916932106018},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48485076427459717},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4755147099494934},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.43557676672935486},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38132262229919434},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3538125157356262},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07997837662696838},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tifs.2024.3451356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tifs.2024.3451356","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"},{"id":"pmh:oai:figshare.com:article/27147699","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Using_Graph_Neural_Networks_to_Improve_Generalization_Capability_of_the_Models_for_Deepfake_Detection/27147699","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":null,"raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/27147699","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Using_Graph_Neural_Networks_to_Improve_Generalization_Capability_of_the_Models_for_Deepfake_Detection/27147699","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":null,"raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2030506860","display_name":null,"funder_award_id":"2022GH15","funder_id":"https://openalex.org/F4320321655","funder_display_name":"Science and Technology Development Fund"}],"funders":[{"id":"https://openalex.org/F4320321655","display_name":"Science and Technology Development Fund","ror":"https://ror.org/044vr6g03"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2133665775","https://openalex.org/W2519887557","https://openalex.org/W2888519208","https://openalex.org/W2891145043","https://openalex.org/W2907492528","https://openalex.org/W2909336075","https://openalex.org/W2913399670","https://openalex.org/W2930556772","https://openalex.org/W2963091558","https://openalex.org/W2963684180","https://openalex.org/W2963720850","https://openalex.org/W2982058372","https://openalex.org/W2982232682","https://openalex.org/W2984516443","https://openalex.org/W2997615092","https://openalex.org/W3021344608","https://openalex.org/W3034196597","https://openalex.org/W3034552680","https://openalex.org/W3034713808","https://openalex.org/W3034864980","https://openalex.org/W3034900344","https://openalex.org/W3035061161","https://openalex.org/W3035669277","https://openalex.org/W3036806226","https://openalex.org/W3103928107","https://openalex.org/W3108854358","https://openalex.org/W3138516171","https://openalex.org/W3158353280","https://openalex.org/W3174508664","https://openalex.org/W3174656926","https://openalex.org/W3175342695","https://openalex.org/W3176241004","https://openalex.org/W3183392865","https://openalex.org/W3183999072","https://openalex.org/W3191630110","https://openalex.org/W3196204467","https://openalex.org/W4200635057","https://openalex.org/W4205974231","https://openalex.org/W4206482253","https://openalex.org/W4210623456","https://openalex.org/W4214680478","https://openalex.org/W4214947578","https://openalex.org/W4225966148","https://openalex.org/W4283391073","https://openalex.org/W4283792802","https://openalex.org/W4283796843","https://openalex.org/W4283802557","https://openalex.org/W4287080402","https://openalex.org/W4287758545","https://openalex.org/W4288090950","https://openalex.org/W4290994941","https://openalex.org/W4297095254","https://openalex.org/W4312388562","https://openalex.org/W4312782746","https://openalex.org/W4313476637","https://openalex.org/W4313893032","https://openalex.org/W4317796367","https://openalex.org/W4322576470","https://openalex.org/W4323928887","https://openalex.org/W4360993864","https://openalex.org/W4385245566","https://openalex.org/W4390874333","https://openalex.org/W4402774698","https://openalex.org/W6769705151","https://openalex.org/W6775642233","https://openalex.org/W6784810453","https://openalex.org/W6802918380","https://openalex.org/W6839235314","https://openalex.org/W6848935878"],"related_works":["https://openalex.org/W3162204513","https://openalex.org/W2371138613","https://openalex.org/W2048963458","https://openalex.org/W43109613","https://openalex.org/W2359952343","https://openalex.org/W4385627933","https://openalex.org/W2532801570","https://openalex.org/W2480127678","https://openalex.org/W2806270048","https://openalex.org/W4310605282"],"abstract_inverted_index":{"Deepfake":[0],"detection":[1,20,57,98,195],"plays":[2],"a":[3,45,69,90,100,108],"key":[4],"role":[5],"in":[6,13,26,35,234],"preventing":[7],"the":[8,75,83,126,136,141,144,149,154,158,187,220],"misuses":[9],"of":[10,143,224,243,251],"artificial":[11],"intelligence":[12],"video":[14],"editing.":[15],"Current":[16],"deep":[17],"learning-based":[18],"deepfake":[19,56,97],"methods":[21,210],"often":[22],"perform":[23],"quite":[24],"well":[25],"intra-dataset":[27],"testing,":[28],"but":[29],"they":[30],"may":[31],"lose":[32],"good":[33,249],"performance":[34],"cross-dataset":[36],"testing.":[37],"In":[38,51],"other":[39,208],"words,":[40],"generalization":[41,85],"capability":[42],"is":[43],"still":[44],"crucial":[46],"problem":[47],"to":[48,73,81,111,139,157],"be":[49],"resolved.":[50],"this":[52],"paper,":[53],"we":[54,88,106,134],"address":[55],"by":[58,152],"treating":[59],"an":[60],"image":[61,79],"as":[62,68,72,99],"non-Euclidean":[63],"data":[64],"and":[65,119,146,177,183,190,196,227,232],"representing":[66],"it":[67],"graph":[70,91,101,150,163,188],"so":[71],"infer":[74],"informative":[76],"connections":[77,142],"between":[78],"patches/nodes":[80],"improve":[82],"detector\u2019s":[84],"capability.":[86],"Specifically,":[87],"propose":[89,107],"neural":[92,165],"network-based":[93],"paradigm":[94],"that":[95,202],"casts":[96],"binary":[102],"classification":[103,245],"problem.":[104],"First,":[105],"dual-branch":[109],"network":[110],"extract":[112],"node":[113,129,171,175,179,191,244],"features":[114,176,180],"from":[115],"both":[116],"RGB":[117,174],"images":[118,123],"their":[120],"color":[121],"difference":[122],"(CDIs)":[124],"via":[125],"Transformer-based":[127],"trainable":[128],"encoder":[130],"module":[131],"(TNEM).":[132],"Second,":[133],"adopt":[135],"adjacency":[137,159],"matrix":[138],"establish":[140],"nodes":[145],"further":[147],"optimize":[148],"representation":[151],"applying":[153],"adaptive":[155],"threshold":[156],"matrix.":[160],"Third,":[161],"multi-head":[162],"convolutional":[164],"networks":[166],"are":[167,181],"carried":[168],"out":[169],"for":[170,193],"feature":[172],"extraction.":[173],"CDI":[178],"concatenated":[182],"separately":[184],"fed":[185],"into":[186],"classifier":[189,192],"forgery":[194,197],"localization.":[198],"Experimental":[199],"results":[200,246],"demonstrate":[201],"our":[203,217,252],"method":[204],"can":[205],"overall":[206],"outperform":[207],"state-of-the-art":[209],"on":[211,229,238],"7":[212],"popular":[213],"benchmark":[214],"datasets.":[215],"Notably,":[216],"model":[218],"achieves":[219],"highest":[221],"AUC":[222],"values":[223],"96.19%,":[225],"80.99%":[226],"87.68%":[228],"Celeb-DF-V2,":[230],"DFDC":[231],"DFDCP":[233],"turn":[235],"when":[236],"trained":[237],"FF++":[239],"(C23).":[240],"The":[241],"visualization":[242],"also":[247],"provides":[248],"interpretability":[250],"proposed":[253],"approach.":[254]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}