{"id":"https://openalex.org/W7124173194","doi":"https://doi.org/10.1109/icpads67057.2025.11322961","title":"Aurora: Adaptive Audio-Video Multi-Scale Attention Fusion for Deepfake Detection","display_name":"Aurora: Adaptive Audio-Video Multi-Scale Attention Fusion for Deepfake Detection","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124173194","doi":"https://doi.org/10.1109/icpads67057.2025.11322961"},"language":null,"primary_location":{"id":"doi:10.1109/icpads67057.2025.11322961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11322961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","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/A5101866162","display_name":"Jie Xu","orcid":"https://orcid.org/0000-0001-8620-1353"},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jie Xu","raw_affiliation_strings":["*School of Computer Science and Technology, Donghua University,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"*School of Computer Science and Technology, Donghua University,Shanghai,China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122997248","display_name":"Shan Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I181326427","display_name":"Donghua University","ror":"https://ror.org/035psfh38","country_code":"CN","type":"education","lineage":["https://openalex.org/I181326427"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Chang","raw_affiliation_strings":["*School of Computer Science and Technology, Donghua University,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"*School of Computer Science and Technology, Donghua University,Shanghai,China","institution_ids":["https://openalex.org/I181326427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123002583","display_name":"Hongzi Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzi Zhu","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Computer Science and Engineering,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101866162"],"corresponding_institution_ids":["https://openalex.org/I181326427"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.69408797,"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":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5188000202178955,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5188000202178955,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.44290000200271606,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.00419999985024333,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6104999780654907},{"id":"https://openalex.org/keywords/concatenation","display_name":"Concatenation (mathematics)","score":0.5436999797821045},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4300999939441681},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42410001158714294},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3984000086784363},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.3732999861240387},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.31209999322891235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.807699978351593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6401000022888184},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6104999780654907},{"id":"https://openalex.org/C87619178","wikidata":"https://www.wikidata.org/wiki/Q126002","display_name":"Concatenation (mathematics)","level":2,"score":0.5436999797821045},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4300999939441681},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3984000086784363},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36820000410079956},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32679998874664307},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.3084000051021576},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.30469998717308044},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.29510000348091125},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2718000113964081},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.27070000767707825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpads67057.2025.11322961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11322961","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5705159902572632,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2041439392","https://openalex.org/W3107306308","https://openalex.org/W3156100202","https://openalex.org/W3166812855","https://openalex.org/W3197123936","https://openalex.org/W4213449918","https://openalex.org/W4214691743","https://openalex.org/W4282968242","https://openalex.org/W4285419745","https://openalex.org/W4297498506","https://openalex.org/W4312095999","https://openalex.org/W4312472072","https://openalex.org/W4320882980","https://openalex.org/W4360993864","https://openalex.org/W4375869371","https://openalex.org/W4385805162","https://openalex.org/W4386928847","https://openalex.org/W4387359777","https://openalex.org/W4392412686","https://openalex.org/W4392904345","https://openalex.org/W4398787762","https://openalex.org/W4398789263","https://openalex.org/W4401028289","https://openalex.org/W4403780881","https://openalex.org/W4403791806","https://openalex.org/W4404954991","https://openalex.org/W4408354631","https://openalex.org/W4409427122","https://openalex.org/W4410342306","https://openalex.org/W4413158744"],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,8,147,161],"rapid":[2],"advancement":[3],"of":[4,10,55,135,155,164],"generative":[5],"forgery":[6,32,136],"technologies,":[7],"detection":[9,144],"multi-modal":[11],"deepfake":[12,143],"audio-video":[13,28],"content":[14],"has":[15],"become":[16],"an":[17,92,152,158],"urgent":[18],"demand":[19],"in":[20,142],"cyber":[21],"security":[22],"and":[23,38,108,122,131,157],"forensic":[24],"analysis.":[25],"However,":[26],"detecting":[27],"deepfakes":[29],"remains":[30],"challenging:":[31],"traces":[33],"are":[34],"often":[35,104],"subtle,":[36],"dispersed,":[37],"highly":[39],"resolution-dependent;":[40],"existing":[41],"multimodal":[42],"methods":[43],"rely":[44],"on":[45],"simple":[46],"concatenation":[47],"or":[48],"shallow":[49],"interactions,":[50],"leading":[51,138],"to":[52,99,116,139],"insufficient":[53],"exploitation":[54],"cross-modal":[56,133],"consistency.":[57],"To":[58],"address":[59],"these":[60],"issues,":[61],"we":[62,90],"propose":[63],"a":[64,109],"Cross-level":[65],"Multi-modal":[66],"Fusion":[67],"(CLMF)":[68],"framework":[69],"that":[70],"progressively":[71],"integrates":[72],"audio":[73],"cues":[74],"into":[75],"visual":[76],"representations":[77],"through":[78],"cross-level":[79],"attention,":[80],"adaptively":[81],"enhancing":[82],"complementary":[83],"information":[84],"while":[85],"suppressing":[86],"redundancy.":[87],"In":[88],"addition,":[89],"design":[91],"Adaptive":[93],"Audio":[94],"Feature":[95,112],"Enhancement":[96,113],"module":[97,114],"(AAFE)":[98],"highlight":[100],"subtle":[101],"frequencydomain":[102],"artifacts":[103],"masked":[105],"by":[106],"noise,":[107],"Multi-scale":[110],"Visual":[111],"(MVFE)":[115],"capture":[117],"both":[118],"local":[119],"texture":[120],"inconsistencies":[121],"global":[123],"structural":[124],"distortions.":[125],"These":[126],"components":[127],"jointly":[128],"achieve":[129],"robust":[130],"consistent":[132],"alignment":[134],"traces,":[137],"significant":[140],"improvements":[141],"performance.":[145,168],"On":[146],"FakeAVCeleb":[148],"benchmark,":[149],"AURORA":[150],"achieves":[151],"accuracy":[153],"(ACC)":[154],"94.32%":[156],"area":[159],"under":[160],"curve":[162],"(AUC)":[163],"93.66%,":[165],"demonstrating":[166],"superior":[167]},"counts_by_year":[],"updated_date":"2026-01-16T23:16:36.188383","created_date":"2026-01-15T00:00:00"}