{"id":"https://openalex.org/W4414985048","doi":"https://doi.org/10.1145/3774904.3792220","title":"MGFFD-VLM: Multi-Granularity Prompt Learning for Face Forgery Detection with VLM","display_name":"MGFFD-VLM: Multi-Granularity Prompt Learning for Face Forgery Detection with VLM","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W4414985048","doi":"https://doi.org/10.1145/3774904.3792220"},"language":"en","primary_location":{"id":"doi:10.1145/3774904.3792220","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792220","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792220","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012861613","display_name":"Tao Chen","orcid":"https://orcid.org/0000-0002-9474-1947"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Chen","raw_affiliation_strings":["Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0009-0006-0488-5741","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458628","display_name":"Jingyi Zhang","orcid":"https://orcid.org/0000-0002-8172-5104"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingyi Zhang","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"raw_orcid":"https://orcid.org/0009-0002-7857-9588","affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058058294","display_name":"Decheng Liu","orcid":"https://orcid.org/0000-0002-6550-212X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]},{"id":"https://openalex.org/I4210141776","display_name":"China XD Group (China)","ror":"https://ror.org/04ceqst84","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210141776"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Decheng Liu","raw_affiliation_strings":["Xidian Unviersity, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-6550-212X","affiliations":[{"raw_affiliation_string":"Xidian Unviersity, Xi'an, China","institution_ids":["https://openalex.org/I149594827","https://openalex.org/I4210141776"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012655281","display_name":"Chunlei Peng","orcid":"https://orcid.org/0000-0003-3448-2514"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]},{"id":"https://openalex.org/I4210141776","display_name":"China XD Group (China)","ror":"https://ror.org/04ceqst84","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210141776"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlei Peng","raw_affiliation_strings":["Xidian Unviersity, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0003-3448-2514","affiliations":[{"raw_affiliation_string":"Xidian Unviersity, Xi'an, China","institution_ids":["https://openalex.org/I149594827","https://openalex.org/I4210141776"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"2707","last_page":"2715"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.954200029373169,"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"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.954200029373169,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9287999868392944,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9125000238418579,"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":0.7540000081062317},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.654699981212616},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5289999842643738},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5121999979019165},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5019999742507935},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.48750001192092896},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.35199999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896000146865845},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7540000081062317},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.654699981212616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6431000232696533},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5289999842643738},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5121999979019165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5045999884605408},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5019999742507935},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.48750001192092896},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.35199999809265137},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.34119999408721924},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.33329999446868896},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.30410000681877136},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2768999934196472},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3774904.3792220","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792220","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.12232","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.12232","pdf_url":"https://arxiv.org/pdf/2507.12232","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.12232","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.12232","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:10.1145/3774904.3792220","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792220","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"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":{"The":[0],"proliferation":[1],"of":[2,22,146,153,175],"face":[3,59,67,111],"forgery":[4,34,77,160,197,207,236],"content":[5],"on":[6],"the":[7,20,66,135,173],"Web":[8],"poses":[9],"a":[10,60,68,143,149,158,189],"severe":[11],"threat":[12],"to":[13,30,53,81,138,171],"online":[14],"trust,":[15],"social":[16],"media":[17],"security,":[18],"and":[19,36,79,86,121,148,188,196,238],"credibility":[21],"digital":[23],"information.":[24],"Existing":[25],"detection":[26,161,216],"approaches":[27],"often":[28,116],"fail":[29],"generalize":[31],"across":[32],"diverse":[33,151],"types":[35],"unseen":[37],"scenarios":[38],"commonly":[39],"encountered":[40],"in":[41,118,233],"web-scale":[42],"applications.":[43],"Recent":[44],"studies":[45,71],"have":[46,102],"utilized":[47],"visual":[48],"large":[49],"language":[50],"models":[51],"(VLMs)":[52],"answer":[54],"not":[55,108,204],"only":[56,205],"''Is":[57],"this":[58,131],"forgery?''":[61,69],"but":[62,209],"also":[63,210],"''Why":[64],"is":[65],"These":[70],"introduced":[72],"forgery-related":[73,221],"attributes,":[74,113],"such":[75],"as":[76],"location":[78],"type,":[80],"construct":[82],"deepfake":[83],"VQA":[84,136],"datasets":[85],"train":[87],"VLMs,":[88],"achieving":[89,240],"high":[90],"accuracy":[91],"while":[92],"providing":[93],"human-understandable":[94],"explanatory":[95],"text":[96],"descriptions.":[97],"However,":[98],"these":[99],"methods":[100,232],"still":[101],"limitations.":[103],"For":[104],"example,":[105],"they":[106,122],"do":[107],"fully":[109],"leverage":[110],"quality-related":[112],"which":[114,141,164],"are":[115],"abnormal":[117],"forged":[119],"faces,":[120],"lack":[123],"effective":[124],"training":[125],"strategies":[126],"for":[127],"forgery-aware":[128],"VLMs.":[129],"In":[130],"paper,":[132],"we":[133,156,218],"extend":[134],"dataset":[137],"create":[139],"DD-VQA+,":[140],"features":[142],"richer":[144],"set":[145],"attributes":[147],"more":[150],"range":[152],"samples.":[154],"Furthermore,":[155],"introduce":[157],"novel":[159],"framework,":[162],"MGFFD-VLM,":[163],"integrates":[165],"an":[166],"Attribute-Driven":[167],"Hybrid":[168],"LoRA":[169],"Strategy":[170],"enhance":[172],"capabilities":[174],"Visual":[176],"Large":[177],"Language":[178],"Models":[179],"(VLMs).":[180],"Additionally,":[181],"our":[182,202,228],"framework":[183],"incorporates":[184],"Multi-Granularity":[185],"Prompt":[186],"Learning":[187],"Forgery-Aware":[190],"Training":[191],"Strategy.":[192],"By":[193],"transforming":[194],"classification":[195,208],"segmentation":[198],"results":[199,225],"into":[200],"prompts,":[201],"method":[203],"improves":[206],"enhances":[211],"interpretability.":[212],"To":[213],"further":[214],"boost":[215],"performance,":[217],"design":[219],"multiple":[220],"auxiliary":[222],"losses.":[223],"Experimental":[224],"demonstrate":[226],"that":[227],"approach":[229],"surpasses":[230],"existing":[231],"both":[234],"text-based":[235],"judgment":[237],"analysis,":[239],"superior":[241],"accuracy.":[242]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-09T00:00:00"}