{"id":"https://openalex.org/W7134804323","doi":"https://doi.org/10.48550/arxiv.2603.08483","title":"X-AVDT: Audio-Visual Cross-Attention for Robust Deepfake Detection","display_name":"X-AVDT: Audio-Visual Cross-Attention for Robust Deepfake Detection","publication_year":2026,"publication_date":"2026-03-09","ids":{"openalex":"https://openalex.org/W7134804323","doi":"https://doi.org/10.48550/arxiv.2603.08483"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.08483","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.08483","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.08483","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128674131","display_name":"Youngseo Kim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Youngseo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128687178","display_name":"Kwan Yun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun, Kwan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101233330","display_name":"Seokhyeon Hong","orcid":"https://orcid.org/0000-0002-8490-5338"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, Seokhyeon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089278031","display_name":"Sihun Cha","orcid":"https://orcid.org/0000-0001-9506-9438"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cha, Sihun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128652279","display_name":"Colette Suhjung Koo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koo, Colette Suhjung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128647553","display_name":"Junyong Noh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noh, Junyong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9480999708175659,"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":0.9480999708175659,"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":0.015799999237060547,"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/T11448","display_name":"Face recognition and analysis","score":0.004999999888241291,"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/robustness","display_name":"Robustness (evolution)","score":0.7657999992370605},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6204000115394592},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5142999887466431},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.4221000075340271},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3978999853134155},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.3880999982357025},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.36169999837875366}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7657999992370605},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7645000219345093},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6204000115394592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.612500011920929},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5142999887466431},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.446399986743927},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4221000075340271},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3880999982357025},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.36169999837875366},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.35670000314712524},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.28619998693466187},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.272599995136261},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.08483","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.08483","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.08483","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.08483","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7515606880187988,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"surge":[1],"of":[2,17,164],"highly":[3],"realistic":[4],"synthetic":[5],"videos":[6],"produced":[7],"by":[8,157],"contemporary":[9],"generative":[10],"systems":[11],"has":[12],"significantly":[13],"increased":[14],"the":[15,162],"risk":[16],"malicious":[18],"use,":[19],"challenging":[20],"both":[21],"humans":[22],"and":[23,34,63,92,122,130,142,148],"existing":[24,152],"detectors.":[25],"Against":[26],"this":[27,56],"backdrop,":[28],"we":[29,58,109],"take":[30],"a":[31,61,86,113],"generator-side":[32],"view":[33],"observe":[35],"that":[36,67,135],"internal":[37,166],"cross-attention":[38,96],"mechanisms":[39],"in":[40,175],"these":[41,78],"models":[42],"encode":[43],"fine-grained":[44],"speech-motion":[45],"alignment,":[46],"offering":[47],"useful":[48],"correspondence":[49],"cues":[50,169],"for":[51,170],"forgery":[52],"detection.":[53,177],"Building":[54],"on":[55,140],"insight,":[57],"propose":[59],"X-AVDT,":[60],"robust":[62],"generalizable":[64],"deepfake":[65,116,176],"detector":[66],"probes":[68],"generator-internal":[69],"audio-visual":[70,95,167],"signals":[71],"accessed":[72],"via":[73],"DDIM":[74],"inversion":[75],"to":[76,145,172],"expose":[77],"cues.":[79],"X-AVDT":[80,136],"extracts":[81],"two":[82],"complementary":[83],"signals:":[84],"(i)":[85],"video":[87],"composite":[88],"capturing":[89],"inversion-induced":[90],"discrepancies,":[91],"(ii)":[93],"an":[94],"feature":[97],"reflecting":[98],"modality":[99],"alignment":[100],"enforced":[101],"during":[102],"generation.":[103],"To":[104],"enable":[105],"faithful":[106],"cross-generator":[107],"evaluation,":[108],"further":[110],"introduce":[111],"MMDF,":[112],"new":[114],"multimodal":[115],"dataset":[117],"spanning":[118],"diverse":[119],"manipulation":[120],"types":[121],"rapidly":[123],"evolving":[124],"synthesis":[125],"paradigms,":[126],"including":[127],"GANs,":[128],"diffusion,":[129],"flow-matching.":[131],"Extensive":[132],"experiments":[133],"demonstrate":[134],"achieves":[137],"leading":[138],"performance":[139],"MMDF":[141],"generalizes":[143],"strongly":[144],"external":[146],"benchmarks":[147],"unseen":[149],"generators,":[150],"outperforming":[151],"methods":[153],"with":[154],"accuracy":[155],"improved":[156],"13.1%.":[158],"Our":[159],"findings":[160],"highlight":[161],"importance":[163],"leveraging":[165],"consistency":[168],"robustness":[171],"future":[173],"generators":[174]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-11T00:00:00"}