{"id":"https://openalex.org/W7138901288","doi":"https://doi.org/10.48550/arxiv.2603.17761","title":"Evidence Packing for Cross-Domain Image Deepfake Detection with LVLMs","display_name":"Evidence Packing for Cross-Domain Image Deepfake Detection with LVLMs","publication_year":2026,"publication_date":"2026-03-18","ids":{"openalex":"https://openalex.org/W7138901288","doi":"https://doi.org/10.48550/arxiv.2603.17761"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.17761","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.17761","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.17761","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130078453","display_name":"Yuxin Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yuxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129999784","display_name":"Fei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129988961","display_name":"Kun Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Kun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130063656","display_name":"Yiqi Nie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nie, Yiqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130008485","display_name":"Junjie Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Junjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080759198","display_name":"Zhangling Duan","orcid":"https://orcid.org/0000-0003-3246-8022"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duan, Zhangling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5123416761","display_name":"Zhaohong Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Zhaohong","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":0.8557000160217285,"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":0.8557000160217285,"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":0.04749999940395355,"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":0.0406000018119812,"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/set","display_name":"Set (abstract data type)","score":0.6086999773979187},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5935999751091003},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5723000168800354},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5083000063896179},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.4404999911785126},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.43050000071525574},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4090000092983246},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.3935000002384186}],"concepts":[{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6086999773979187},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5935999751091003},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5723000168800354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5580999851226807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.519599974155426},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5083000063896179},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.43050000071525574},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4090000092983246},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3935000002384186},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3377000093460083},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3100999891757965},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C2776196576","wikidata":"https://www.wikidata.org/wiki/Q196113","display_name":"Camouflage","level":2,"score":0.29820001125335693},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2822999954223633},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25940001010894775},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.17761","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.17761","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.17761","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.17761","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":"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":{"Image":[0],"Deepfake":[1],"Detection":[2],"(IDD)":[3],"separates":[4],"manipulated":[5],"images":[6],"from":[7],"authentic":[8],"ones":[9],"by":[10],"spotting":[11],"artifacts":[12],"of":[13,65],"synthesis":[14],"or":[15],"tampering.":[16],"Although":[17],"large":[18],"vision-language":[19],"models":[20],"(LVLMs)":[21],"offer":[22],"strong":[23,143],"image":[24],"understanding,":[25],"adapting":[26],"them":[27],"to":[28,37],"IDD":[29],"often":[30],"demands":[31],"costly":[32],"fine-tuning":[33],"and":[34,91,110,121],"generalizes":[35],"poorly":[36],"diverse,":[38],"evolving":[39],"manipulations.":[40],"We":[41],"propose":[42],"the":[43,76],"Semantic":[44],"Consistent":[45],"Evidence":[46],"Pack":[47],"(SCEP),":[48],"a":[49,62,82,95,115,131],"training-free":[50],"LVLM":[51,133,146],"framework":[52],"that":[53,69,129],"replaces":[54],"whole-image":[55],"inference":[56],"with":[57,94,102],"evidence-driven":[58],"reasoning.":[59],"SCEP":[60,113,141],"mines":[61],"compact":[63],"set":[64],"suspicious":[66],"patch":[67,86],"tokens":[68],"best":[70],"reveal":[71],"manipulation":[72],"cues.":[73],"It":[74],"uses":[75],"vision":[77],"encoder's":[78],"CLS":[79],"token":[80],"as":[81],"global":[83],"reference,":[84],"clusters":[85],"features":[87],"into":[88],"coherent":[89],"groups,":[90],"scores":[92],"patches":[93,118],"fused":[96],"metric":[97],"combining":[98],"CLS-guided":[99],"semantic":[100],"mismatch":[101],"frequency-and":[103],"noise-based":[104],"anomalies.":[105],"To":[106],"cover":[107],"dispersed":[108],"traces":[109],"avoid":[111],"redundancy,":[112],"samples":[114],"few":[116],"high-confidence":[117],"per":[119],"cluster":[120],"applies":[122],"grid-based":[123],"NMS,":[124],"producing":[125],"an":[126],"evidence":[127],"pack":[128],"conditions":[130],"frozen":[132],"for":[134],"prediction.":[135],"Experiments":[136],"on":[137],"diverse":[138],"benchmarks":[139],"show":[140],"outperforms":[142],"baselines":[144],"without":[145],"fine-tuning.":[147]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-20T00:00:00"}