{"id":"https://openalex.org/W7153025837","doi":"https://doi.org/10.48550/arxiv.2604.07741","title":"MSCT: Differential Cross-Modal Attention for Deepfake Detection","display_name":"MSCT: Differential Cross-Modal Attention for Deepfake Detection","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7153025837","doi":"https://doi.org/10.48550/arxiv.2604.07741"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.07741","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.07741","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2604.07741","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133325902","display_name":"Fangda Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Fangda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133320044","display_name":"Miao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Miao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016067537","display_name":"Yuchenqu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yingxue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100378384","display_name":"Jing Wang","orcid":"https://orcid.org/0000-0001-8549-852X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133355393","display_name":"Shenghui Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Shenghui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133371875","display_name":"NAN LI","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Nan","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":0.7942000031471252,"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":0.7942000031471252,"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":0.17180000245571136,"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":0.004399999976158142,"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/fuse","display_name":"Fuse (electrical)","score":0.6553000211715698},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5306000113487244},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5170000195503235},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.503000020980835},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4912000000476837},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4659000039100647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7125999927520752},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.6553000211715698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5763000249862671},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5306000113487244},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5170000195503235},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.503000020980835},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4912000000476837},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35339999198913574},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3181999921798706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.27079999446868896},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.07741","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.07741","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.07741","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.07741","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Audio-visual":[0],"deepfake":[1,66],"detection":[2,41],"typically":[3],"employs":[4],"a":[5,59,71,82],"complementary":[6],"multi-modal":[7,39,88],"model":[8],"to":[9,74,86],"check":[10],"the":[11,15,29,37,44,76,96,100,103],"forgery":[12,21,40],"traces":[13,22],"in":[14],"video.":[16],"These":[17],"methods":[18],"primarily":[19],"extract":[20],"through":[23],"audio-visual":[24],"alignment,":[25],"which":[26],"results":[27],"from":[28],"inconsistency":[30],"between":[31],"audio":[32],"and":[33,50,81],"video":[34],"modalities.":[35],"However,":[36],"traditional":[38],"method":[42],"has":[43],"problem":[45],"of":[46,78,102],"insufficient":[47],"feature":[48],"extraction":[49],"modal":[51],"alignment":[52],"deviation.":[53],"To":[54],"address":[55],"this,":[56],"we":[57],"propose":[58],"multi-scale":[60,72],"cross-modal":[61,84],"transformer":[62],"encoder":[63],"(MSCT)":[64],"for":[65],"detection.":[67],"Our":[68,90],"approach":[69],"includes":[70],"self-attention":[73],"integrate":[75],"features":[77],"adjacent":[79],"embeddings":[80],"differential":[83],"attention":[85],"fuse":[87],"features.":[89],"experiments":[91],"demonstrate":[92],"competitive":[93],"performance":[94],"on":[95],"FakeAVCeleb":[97],"dataset,":[98],"validating":[99],"effectiveness":[101],"proposed":[104],"structure.":[105]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-11T00:00:00"}