{"id":"https://openalex.org/W4399418483","doi":"https://doi.org/10.1145/3652583.3658035","title":"CLIPping the Deception: Adapting Vision-Language Models for Universal Deepfake Detection","display_name":"CLIPping the Deception: Adapting Vision-Language Models for Universal Deepfake Detection","publication_year":2024,"publication_date":"2024-05-30","ids":{"openalex":"https://openalex.org/W4399418483","doi":"https://doi.org/10.1145/3652583.3658035"},"language":"en","primary_location":{"id":"doi:10.1145/3652583.3658035","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658035","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658035","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 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658035","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018346537","display_name":"Sohail Ahmed Khan","orcid":"https://orcid.org/0000-0001-5351-2278"},"institutions":[{"id":"https://openalex.org/I4432739","display_name":"University of Bergen","ror":"https://ror.org/03zga2b32","country_code":"NO","type":"education","lineage":["https://openalex.org/I4432739"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Sohail Ahmed Khan","raw_affiliation_strings":["University of Bergen, Norway, Bergen, NO"],"raw_orcid":"https://orcid.org/0000-0001-5351-2278","affiliations":[{"raw_affiliation_string":"University of Bergen, Norway, Bergen, NO","institution_ids":["https://openalex.org/I4432739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064606251","display_name":"Duc\u2010Tien Dang\u2010Nguyen","orcid":"https://orcid.org/0000-0002-2761-2213"},"institutions":[{"id":"https://openalex.org/I4432739","display_name":"University of Bergen","ror":"https://ror.org/03zga2b32","country_code":"NO","type":"education","lineage":["https://openalex.org/I4432739"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Duc-Tien Dang-Nguyen","raw_affiliation_strings":["University of Bergen, Norway, Bergen, NO"],"raw_orcid":"https://orcid.org/0000-0002-2761-2213","affiliations":[{"raw_affiliation_string":"University of Bergen, Norway, Bergen, NO","institution_ids":["https://openalex.org/I4432739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5018346537"],"corresponding_institution_ids":["https://openalex.org/I4432739"],"apc_list":null,"apc_paid":null,"fwci":10.2373,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.98901367,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1006","last_page":"1015"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9991000294685364,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9991000294685364,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9986000061035156,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9754999876022339,"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/computer-science","display_name":"Computer science","score":0.8804724812507629},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.7628616690635681},{"id":"https://openalex.org/keywords/deception","display_name":"Deception","score":0.6477603912353516},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5681399703025818},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.566172182559967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5443146228790283},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5070126056671143},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4803820252418518},{"id":"https://openalex.org/keywords/clipping","display_name":"Clipping (morphology)","score":0.45653045177459717},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44023799896240234},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.0739995539188385}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8804724812507629},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.7628616690635681},{"id":"https://openalex.org/C2779267917","wikidata":"https://www.wikidata.org/wiki/Q170028","display_name":"Deception","level":2,"score":0.6477603912353516},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5681399703025818},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.566172182559967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5443146228790283},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5070126056671143},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4803820252418518},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.45653045177459717},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44023799896240234},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0739995539188385},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652583.3658035","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658035","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658035","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 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652583.3658035","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652583.3658035","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652583.3658035","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 2024 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.41999998688697815,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399418483.pdf"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W2112796928","https://openalex.org/W2194775991","https://openalex.org/W2909336075","https://openalex.org/W2950352474","https://openalex.org/W2962770929","https://openalex.org/W2962793481","https://openalex.org/W2962974533","https://openalex.org/W2963767194","https://openalex.org/W2963800363","https://openalex.org/W2982058372","https://openalex.org/W3019200173","https://openalex.org/W3034577585","https://openalex.org/W3035574324","https://openalex.org/W3125803510","https://openalex.org/W3173126908","https://openalex.org/W3174807077","https://openalex.org/W3180355996","https://openalex.org/W3183392865","https://openalex.org/W3185341429","https://openalex.org/W3198377975","https://openalex.org/W3198675127","https://openalex.org/W4225323055","https://openalex.org/W4281485151","https://openalex.org/W4312453532","https://openalex.org/W4312651322","https://openalex.org/W4312753047","https://openalex.org/W4312933868","https://openalex.org/W4375869427","https://openalex.org/W4386071953","https://openalex.org/W4389370799","https://openalex.org/W6797179183","https://openalex.org/W6931405348"],"related_works":["https://openalex.org/W2165717120","https://openalex.org/W2039390456","https://openalex.org/W2948663225","https://openalex.org/W2029954793","https://openalex.org/W1992683634","https://openalex.org/W4295295666","https://openalex.org/W1978059949","https://openalex.org/W2512387791","https://openalex.org/W70044515","https://openalex.org/W4394775207"],"abstract_inverted_index":{"The":[0],"recent":[1,64],"advancements":[2],"in":[3,74,84,93],"Generative":[4],"Adversarial":[5],"Networks":[6],"(GANs)":[7],"and":[8,22,125,143,196,200],"the":[9,17,43,54,102,117,123,136,153,164],"emergence":[10],"of":[11,19,56,105,152,167],"Diffusion":[12],"models":[13,59],"have":[14],"significantly":[15],"streamlined":[16],"production":[18],"highly":[20],"realistic":[21],"widely":[23],"accessible":[24],"synthetic":[25],"content.":[26],"As":[27],"a":[28,32,80,173],"result,":[29],"there":[30],"is":[31,120],"pressing":[33],"need":[34],"for":[35,67,89],"effective":[36],"general":[37],"purpose":[38],"detection":[39],"mechanisms":[40],"to":[41,86,95,160],"mitigate":[42],"potential":[44],"risks":[45],"posed":[46],"by":[47,140,193],"deepfakes.":[48],"In":[49],"this":[50,75],"paper,":[51],"we":[52,77,133,171],"explore":[53],"effectiveness":[55],"pre-trained":[57,201],"vision-language":[58],"(VLMs)":[60],"when":[61],"paired":[62],"with":[63],"adaptation":[65,130],"methods":[66],"universal":[68],"deepfake":[69,90],"detection.":[70,91],"Following":[71],"previous":[72,137],"studies":[73],"domain,":[76],"employ":[78,134],"only":[79],"single":[81],"dataset":[82],"(ProGAN)":[83],"order":[85],"adapt":[87],"CLIP":[88,106],"However,":[92],"contrast":[94],"prior":[96],"research,":[97],"which":[98],"rely":[99],"solely":[100],"on":[101,183],"visual":[103],"part":[104,119],"while":[107,146],"ignoring":[108],"its":[109],"textual":[110],"component,":[111],"our":[112,168],"analysis":[113],"reveals":[114],"that":[115,132],"retaining":[116],"text":[118],"crucial.":[121],"Consequently,":[122],"simple":[124],"lightweight":[126],"Prompt":[127],"Tuning":[128],"based":[129],"strategy":[131],"outperforms":[135],"SOTA":[138],"approach":[139],"5.01%":[141],"mAP":[142],"6.61%":[144],"accuracy":[145],"utilizing":[147],"less":[148],"than":[149],"one":[150],"third":[151],"training":[154],"data":[155],"(200k":[156],"images":[157,184],"as":[158],"compared":[159],"720k).":[161],"To":[162],"assess":[163],"real-world":[165],"applicability":[166],"proposed":[169],"models,":[170],"conduct":[172],"comprehensive":[174],"evaluation":[175],"across":[176],"various":[177],"scenarios.":[178],"This":[179],"involves":[180],"rigorous":[181],"testing":[182],"sourced":[185],"from":[186],"21":[187],"distinct":[188],"datasets,":[189],"including":[190],"those":[191],"generated":[192],"GANs-based,":[194],"diffusion-based":[195],"commercial":[197],"tools.":[198],"Code":[199],"models:":[202],"https://github.com/sohailahmedkhan/CLIPping-the-Deception":[203]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":33},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}