{"id":"https://openalex.org/W7154618583","doi":"https://doi.org/10.48550/arxiv.2604.13660","title":"VRAG-DFD: Verifiable Retrieval-Augmentation for MLLM-based Deepfake Detection","display_name":"VRAG-DFD: Verifiable Retrieval-Augmentation for MLLM-based Deepfake Detection","publication_year":2026,"publication_date":"2026-04-15","ids":{"openalex":"https://openalex.org/W7154618583","doi":"https://doi.org/10.48550/arxiv.2604.13660"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.13660","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.13660","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.2604.13660","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133737508","display_name":"Hui Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Hui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133796978","display_name":"Shunli Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shunli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133823600","display_name":"Yandan Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Yandan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133822283","display_name":"Taiping Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Taiping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133819905","display_name":"Shouhong Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Shouhong","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":0.5530999898910522,"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":0.5530999898910522,"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/T10028","display_name":"Topic Modeling","score":0.10279999673366547,"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"}},{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.02539999969303608,"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/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.7547000050544739},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.703000009059906},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.353300005197525},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3434999883174896},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.31369999051094055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7716000080108643},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.7547000050544739},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.703000009059906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5336999893188477},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34200000762939453},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.22050000727176666}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.13660","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.13660","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.2604.13660","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.13660","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":[{"score":0.48890992999076843,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,138,160],"Deepfake":[1],"Detection":[2],"(DFD)":[3],"tasks,":[4],"researchers":[5],"proposed":[6],"two":[7,41,72,117],"types":[8],"of":[9,25,32,81,113,140,157,162],"MLLM-based":[10],"methods:":[11],"complementary":[12],"combination":[13,80],"with":[14,58,74,99,119],"small":[15],"DFD":[16,126,171],"detectors,":[17],"or":[18],"static":[19],"forgery":[20,27,49,102],"knowledge":[21,28,50,103,127],"injection.":[22],"The":[23],"lack":[24],"professional":[26],"hinders":[29],"the":[30,79,96,153,158],"performance":[31,169],"these":[33],"DFD-MLLMs.":[34],"To":[35],"solve":[36],"this,":[37],"we":[38,67,94,115,143],"deeply":[39],"considered":[40],"insightful":[42],"issues:":[43],"How":[44,54],"to":[45,55,69,150],"provide":[46],"high-quality":[47],"associated":[48],"for":[51,125,134],"MLLMs?":[52],"AND":[53],"endow":[56],"MLLMs":[57],"critical":[59,107,135,154],"reasoning":[60,108,155],"abilities":[61],"given":[62],"noisy":[63],"reference":[64],"information?":[65],"Notably,":[66],"attempted":[68],"address":[70],"above":[71],"questions":[73],"preliminary":[75],"answers":[76],"by":[77],"leveraging":[78],"Retrieval-Augmented":[82],"Generation":[83],"(RAG)":[84],"and":[85,91,105,129,167],"Reinforcement":[86],"Learning":[87],"(RL).":[88],"Through":[89],"RAG":[90],"RL":[92],"techniques,":[93],"propose":[95],"VRAG-DFD":[97,164],"framework":[98],"accurate":[100],"dynamic":[101],"retrieval":[104],"powerful":[106],"capabilities.":[109],"Specifically,":[110],"in":[111],"terms":[112,139,161],"data,":[114],"constructed":[116],"datasets":[118],"RAG:":[120],"Forensic":[121,130],"Knowledge":[122],"Database":[123],"(FKD)":[124],"annotation,":[128],"Chain-of-Thought":[131],"Dataset":[132],"(F-CoT),":[133],"CoT":[136],"construction.":[137],"model":[141],"training,":[142],"adopt":[144],"a":[145],"three-stage":[146],"training":[147],"method":[148],"(Alignment->SFT->GRPO)":[149],"gradually":[151],"cultivate":[152],"ability":[156],"MLLM.":[159],"performance,":[163],"achieved":[165],"SOTA":[166],"competitive":[168],"on":[170],"generalization":[172],"testing.":[173]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-17T00:00:00"}