{"id":"https://openalex.org/W7140432673","doi":"https://doi.org/10.48550/arxiv.2603.23960","title":"Leave No Stone Unturned: Uncovering Holistic Audio-Visual Intrinsic Coherence for Deepfake Detection","display_name":"Leave No Stone Unturned: Uncovering Holistic Audio-Visual Intrinsic Coherence for Deepfake Detection","publication_year":2026,"publication_date":"2026-03-25","ids":{"openalex":"https://openalex.org/W7140432673","doi":"https://doi.org/10.48550/arxiv.2603.23960"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.23960","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23960","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.23960","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130676579","display_name":"Jielun Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Peng, Jielun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130681211","display_name":"Yabin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yabin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130661615","display_name":"Yaqi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yaqi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130653547","display_name":"Long Kong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kong, Long","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130659721","display_name":"Xiaopeng Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, Xiaopeng","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5130676579"],"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":0.9668999910354614,"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":0.9668999910354614,"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":0.017899999395012856,"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/T11019","display_name":"Image Enhancement Techniques","score":0.002400000113993883,"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/leverage","display_name":"Leverage (statistics)","score":0.6966000199317932},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.597599983215332},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5108000040054321},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.4417000114917755},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.37610000371932983},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.36250001192092896},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.3443000018596649}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7573000192642212},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6966000199317932},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6122000217437744},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.597599983215332},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5108000040054321},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4975000023841858},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.4417000114917755},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.37610000371932983},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.36250001192092896},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3246999979019165},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.31619998812675476},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2985000014305115},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2768999934196472},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.23960","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23960","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.23960","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.23960","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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5859793424606323,"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],"rapid":[1],"progress":[2],"of":[3,37,89,155],"generative":[4],"AI":[5],"has":[6],"enabled":[7],"hyper-realistic":[8],"audio-visual":[9,29,68,116,127],"deepfakes,":[10],"intensifying":[11],"threats":[12],"to":[13,32,47,113],"personal":[14],"security":[15],"and":[16,60,71,95,133,158,169],"social":[17],"trust.":[18],"Most":[19],"existing":[20,150],"deepfake":[21,83,119,128],"detectors":[22,40],"rely":[23,42],"either":[24],"on":[25,43,99,103,161],"uni-modal":[26],"artifacts":[27,45],"or":[28],"discrepancies,":[30],"failing":[31],"jointly":[33],"leverage":[34],"both":[35,131],"sources":[36],"information.":[38],"Moreover,":[39],"that":[41,58,146],"generator-specific":[44],"tend":[46],"exhibit":[48],"degraded":[49],"generalization":[50],"when":[51],"confronted":[52],"with":[53],"unseen":[54],"forgeries.":[55],"We":[56],"argue":[57],"robust":[59],"generalizable":[61],"detection":[62],"should":[63],"be":[64],"grounded":[65],"in":[66],"intrinsic":[67],"coherence":[69],"within":[70],"across":[72,142],"modalities.":[73],"Accordingly,":[74],"we":[75,122],"propose":[76],"HAVIC,":[77],"a":[78,125],"Holistic":[79],"Audio-Visual":[80],"Intrinsic":[81],"Coherence-based":[82],"detector.":[84],"HAVIC":[85,107,147],"first":[86],"learns":[87],"priors":[88],"modality-specific":[90],"structural":[91],"coherence,":[92],"inter-modal":[93],"micro-":[94],"macro-coherence":[96],"by":[97],"pre-training":[98],"authentic":[100],"videos.":[101],"Based":[102],"the":[104,162],"learned":[105],"priors,":[106],"further":[108],"performs":[109],"holistic":[110],"adaptive":[111],"aggregation":[112],"dynamically":[114],"fuse":[115],"features":[117],"for":[118],"detection.":[120],"Additionally,":[121],"introduce":[123],"HiFi-AVDF,":[124],"high-fidelity":[126],"dataset":[129,170],"featuring":[130],"text-to-video":[132],"image-to-video":[134],"forgeries":[135],"from":[136],"state-of-the-art":[137,151],"commercial":[138],"generators.":[139],"Extensive":[140],"experiments":[141],"several":[143],"benchmarks":[144],"demonstrate":[145],"significantly":[148],"outperforms":[149],"methods,":[152],"achieving":[153],"improvements":[154],"9.39%":[156],"AP":[157],"9.37%":[159],"AUC":[160],"most":[163],"challenging":[164],"cross-dataset":[165],"scenario.":[166],"Our":[167],"code":[168],"are":[171],"available":[172],"at":[173],"https://github.com/tuffy-studio/HAVIC.":[174]},"counts_by_year":[],"updated_date":"2026-03-27T06:05:27.210665","created_date":"2026-03-27T00:00:00"}