{"id":"https://openalex.org/W7138267966","doi":"https://doi.org/10.48550/arxiv.2603.14005","title":"Towards Generalizable Deepfake Detection via Real Distribution Bias Correction","display_name":"Towards Generalizable Deepfake Detection via Real Distribution Bias Correction","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138267966","doi":"https://doi.org/10.48550/arxiv.2603.14005"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.14005","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14005","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.14005","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129648127","display_name":"Ming-Hui Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liu, Ming-Hui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129669644","display_name":"Harry Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Harry","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129750081","display_name":"Xin Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Xin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086235570","display_name":"Xin-Shun Xu","orcid":"https://orcid.org/0000-0001-9972-7370"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Xin-Shun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129700264","display_name":"Mohan S. Kankanhalli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kankanhalli, Mohan S.","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5129648127"],"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":0.6538000106811523,"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":0.6538000106811523,"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":0.2687999904155731,"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":0.021700000390410423,"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/property","display_name":"Property (philosophy)","score":0.6144999861717224},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.5633000135421753},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5473999977111816},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5253000259399414},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.48089998960494995},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4641999900341034},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.4438000023365021},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.430400013923645}],"concepts":[{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.6144999861717224},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6010000109672546},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5633000135421753},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5473999977111816},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5253000259399414},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.48089998960494995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4717999994754791},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4641999900341034},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.430400013923645},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.4244000017642975},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.388700008392334},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3702999949455261},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.3499000072479248},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3377000093460083},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.335099995136261},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32199999690055847},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30640000104904175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29670000076293945},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2727000117301941}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.14005","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14005","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.14005","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14005","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7677174806594849}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"To":[0,38],"generalize":[1],"deepfake":[2,210],"detectors":[3],"to":[4,12,44,116,163,193],"future":[5,30],"unseen":[6,194],"forgeries,":[7],"most":[8],"existing":[9],"methods":[10],"attempt":[11],"simulate":[13],"the":[14,46,55,60,65,78,91,98,106,118,127,140,144,147,165,177,183],"dynamically":[15],"evolving":[16],"forgery":[17],"types":[18],"using":[19,133],"available":[20],"source":[21,135],"domain":[22,136],"data.":[23,137],"However,":[24],"predicting":[25],"an":[26],"unbounded":[27],"set":[28],"of":[29,48,59,68,87,113,122,150,176,186],"manipulations":[31],"from":[32,51,125],"limited":[33,134],"prior":[34,156],"examples":[35],"is":[36],"infeasible.":[37],"overcome":[39],"this":[40],"limitation,":[41],"we":[42,76],"propose":[43],"exploit":[45],"invariance":[47],"\\textbf{real":[49],"data}":[50],"two":[52,88,178],"complementary":[53],"perspectives:":[54],"fixed":[56],"population":[57,142],"distribution":[58,120,128],"entire":[61],"real":[62,70,114,151,169,187],"class":[63],"and":[64,97,108,157,170,208],"inherent":[66,148],"Gaussianity":[67,149,166],"individual":[69],"images.":[71],"Building":[72],"on":[73,139],"these":[74],"properties,":[75],"introduce":[77],"Real":[79,92],"Distribution":[80,94],"Bias":[81],"Correction":[82],"(RDBC)":[83],"framework,":[84],"which":[85,126],"consists":[86],"key":[89],"components:":[90],"Population":[93],"Estimation":[95],"module":[96],"Distribution-Sampled":[99],"Feature":[100],"Whitening":[101],"module.":[102],"The":[103],"former":[104],"utilizes":[105,146],"independent":[107],"identically":[109],"distributed":[110],"(\\iid)":[111],"property":[112],"samples":[115],"derive":[117],"normal":[119],"form":[121],"their":[123],"statistics,":[124],"parameters":[129],"can":[130],"be":[131],"estimated":[132],"Based":[138],"learned":[141],"distribution,":[143],"latter":[145],"data":[152],"as":[153],"a":[154,159],"discriminative":[155],"performs":[158],"sampling-based":[160],"whitening":[161],"operation":[162],"amplify":[164],"gap":[167],"between":[168],"fake":[171],"samples.":[172],"Through":[173],"synergistic":[174],"coupling":[175],"modules,":[179],"our":[180],"model":[181],"captures":[182],"real-world":[184],"properties":[185],"samples,":[188],"thereby":[189],"enhancing":[190],"its":[191],"generalizability":[192],"target":[195],"domains.":[196],"Extensive":[197],"experiments":[198],"demonstrate":[199],"that":[200],"RDBC":[201],"achieves":[202],"state-of-the-art":[203],"performance":[204],"in":[205],"both":[206],"in-domain":[207],"cross-domain":[209],"detection.":[211]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}