{"id":"https://openalex.org/W7163891052","doi":"https://doi.org/10.48550/arxiv.2606.06666","title":"Architecture-Adaptive Uncertainty Fusion for Deepfake Detection","display_name":"Architecture-Adaptive Uncertainty Fusion for Deepfake Detection","publication_year":2026,"publication_date":"2026-06-04","ids":{"openalex":"https://openalex.org/W7163891052","doi":"https://doi.org/10.48550/arxiv.2606.06666"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.06666","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06666","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.2606.06666","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035200740","display_name":"Ritesh Sharma","orcid":"https://orcid.org/0000-0002-8542-5096"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharma, Ritesh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056801967","display_name":"Mohammad GhasemiGol","orcid":"https://orcid.org/0000-0001-6661-0942"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ghasemigol, Mohammad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5061499121","display_name":"Yuichi Motai","orcid":"https://orcid.org/0000-0002-1957-1896"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Motai, Yuichi","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":0.48500001430511475,"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":0.48500001430511475,"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":0.1599999964237213,"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":0.11349999904632568,"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/generalization","display_name":"Generalization","score":0.6008999943733215},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.551800012588501},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5148000121116638},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.43790000677108765},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.4275999963283539},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.3684000074863434}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6008999943733215},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.551800012588501},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5457000136375427},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5148000121116638},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4456999897956848},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.4275999963283539},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C137209882","wikidata":"https://www.wikidata.org/wiki/Q1403517","display_name":"Measurement uncertainty","level":2,"score":0.35929998755455017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3452000021934509},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.31869998574256897},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31459999084472656},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C177803969","wikidata":"https://www.wikidata.org/wiki/Q29205","display_name":"Uncertainty analysis","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2903999984264374},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28679999709129333},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2612999975681305}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.06666","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06666","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.2606.06666","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.06666","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deepfake":[0],"detection":[1],"systems":[2],"achieve":[3,110],"near-perfect":[4],"accuracy":[5],"on":[6,21,69,98,171],"benchmarks,":[7],"yet":[8],"forensic":[9,223],"deployment":[10,212],"demands":[11],"reliable":[12],"prediction":[13,64],"uncertainty.":[14],"Existing":[15],"uncertainty":[16,28,45,61,199],"quantification":[17],"(UQ)":[18],"methods":[19,109],"rely":[20],"single":[22],"sources":[23,46],"and":[24,52,63,78,173,213],"ignore":[25],"that":[26,41],"optimal":[27],"composition":[29],"varies":[30],"across":[31,95,179],"architectures.":[32],"We":[33],"propose":[34],"Correlation-Optimized":[35],"Fusion":[36],"(COF),":[37],"an":[38],"architecture-adaptive":[39],"framework":[40,209],"fuses":[42],"five":[43],"complementary":[44],"--":[47,54],"epistemic,":[48],"aleatoric,":[49],"calibration,":[50],"conformal,":[51],"distributional":[53],"by":[55],"maximizing":[56],"Pearson":[57],"correlation":[58,115,142],"between":[59],"fused":[60],"scores":[62],"errors":[65],"via":[66],"constrained":[67],"optimization":[68],"the":[70,218],"probability":[71],"simplex.":[72],"COF":[73,117,130,158,204],"requires":[74],"no":[75],"model":[76],"modifications":[77],"only":[79],"42":[80],"s":[81],"of":[82,184,195],"weight":[83],"optimization,":[84],"compared":[85],"to":[86,139,153,165,187],"20--45":[87],"h":[88],"for":[89,210,222],"a":[90,101,206],"5-model":[91],"Deep":[92],"Ensemble.":[93],"Evaluation":[94],"eleven":[96,196],"architectures":[97,136,197],"FaceForensics++":[99],"reveals":[100,175],"fundamental":[102],"trade-off:":[103],"under":[104,125],"matched":[105],"train/evaluation":[106],"protocol,":[107],"non-linear":[108],"approximately":[111],"5--6%":[112],"higher":[113,141],"in-domain":[114,182],"than":[116],"(mean":[118,190],"r":[119,144,154,166],"=":[120,145,155,167],"0.438),":[121],"but":[122],"this":[123],"reverses":[124],"distribution":[126],"shift.":[127],"On":[128],"CelebDF,":[129],"outperforms":[131],"Random":[132],"Forest":[133],"in":[134],"9/11":[135],"with":[137,193],"up":[138],"7.3x":[140],"(MaxViT-B:":[143],"0.249":[146],"vs.":[147],"0.034);":[148],"RF":[149],"degrades":[150],"85%":[151],"cross-domain":[152],"0.071,":[156],"whereas":[157],"retains":[159],"substantially":[160],"more":[161],"signal":[162],"(74%":[163],"drop":[164],"0.116).":[168],"Cross-dataset":[169],"evaluation":[170],"CelebDF":[172],"DFDC":[174],"catastrophic":[176],"generalization":[177],"failure":[178],"all":[180],"methods:":[181],"correlations":[183],"0.41--0.47":[185],"collapse":[186],"near-zero":[188],"externally":[189],"degradation":[191],"90.7%),":[192],"seven":[194],"exhibiting":[198],"inversion.":[200],"These":[201],"results":[202],"establish":[203],"as":[205,217],"practical,":[207],"interpretable":[208],"controlled-distribution":[211],"identify":[214],"domain-adaptive":[215],"UQ":[216],"central":[219],"open":[220],"challenge":[221],"deployment.":[224]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-09T00:00:00"}