{"id":"https://openalex.org/W4415004436","doi":"https://doi.org/10.1109/acit65614.2025.11185646","title":"Detecting Deepfake Audio and Video Manipulation with Multimodal Deep Learning","display_name":"Detecting Deepfake Audio and Video Manipulation with Multimodal Deep Learning","publication_year":2025,"publication_date":"2025-09-17","ids":{"openalex":"https://openalex.org/W4415004436","doi":"https://doi.org/10.1109/acit65614.2025.11185646"},"language":"en","primary_location":{"id":"doi:10.1109/acit65614.2025.11185646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acit65614.2025.11185646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 15th International Conference on Advanced Computer Information Technologies (ACIT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101663773","display_name":"Merve Y\u0131ld\u0131r\u0131m","orcid":"https://orcid.org/0000-0001-6834-3470"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Merve Y\u0131ld\u0131r\u0131m","raw_affiliation_strings":["Fırat University,Department of Computer Engineering,Elazığ,Turkey"],"affiliations":[{"raw_affiliation_string":"Fırat University,Department of Computer Engineering,Elazığ,Turkey","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050391785","display_name":"\u0130lhan Ayd\u0131n","orcid":"https://orcid.org/0000-0001-7681-8528"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u0130lhan Ayd\u0131n","raw_affiliation_strings":["Fırat University,Department of Computer Engineering,Elazığ,Turkey"],"affiliations":[{"raw_affiliation_string":"Fırat University,Department of Computer Engineering,Elazığ,Turkey","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101663773"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29554417,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"863","last_page":"867"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.9955000281333923,"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":0.9955000281333923,"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/T10860","display_name":"Speech and Audio Processing","score":0.928600013256073,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9154000282287598,"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/deep-learning","display_name":"Deep learning","score":0.8115000128746033},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6488999724388123},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.628600001335144},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.522599995136261},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.5216000080108643},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5105000138282776},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4562999904155731},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4180000126361847},{"id":"https://openalex.org/keywords/image-manipulation","display_name":"Image manipulation","score":0.383899986743927}],"concepts":[{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.8115000128746033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8101999759674072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.722599983215332},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6488999724388123},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.628600001335144},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.522599995136261},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.5216000080108643},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5105000138282776},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4180000126361847},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.383899986743927},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3806000053882599},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3086000084877014},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.29809999465942383},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.2921000123023987},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.28139999508857727},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acit65614.2025.11185646","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acit65614.2025.11185646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 15th International Conference on Advanced Computer Information Technologies (ACIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W3162424205","https://openalex.org/W3196204467","https://openalex.org/W3202624240","https://openalex.org/W3213515747","https://openalex.org/W4312758842","https://openalex.org/W4395673009","https://openalex.org/W4408018128"],"related_works":[],"abstract_inverted_index":{"The":[0,91,103],"increase":[1,137],"in":[2,6,20],"fake":[3],"media":[4,30],"production":[5],"the":[7,11,100,109,128,138],"digital":[8,29],"age":[9],"and":[10,28,62,83,122,133],"rapid":[12],"development":[13],"of":[14,25,131,140],"deepfake":[15],"technology":[16],"pose":[17],"serious":[18],"threats":[19],"areas":[21],"such":[22],"as":[23],"violation":[24],"individual":[26],"privacy":[27],"integrity.":[31],"Detecting":[32],"these":[33],"forgeries":[34],"is":[35,71,78,106],"becoming":[36],"increasingly":[37],"difficult,":[38],"especially":[39],"for":[40,73],"single-mode":[41],"systems":[42],"that":[43,58,127],"analyze":[44],"only":[45],"visual":[46],"or":[47],"auditory":[48],"data.":[49],"This":[50,124],"study":[51,125],"presents":[52],"a":[53,86,116],"multi-modal":[54],"deep":[55,141],"learning":[56,121],"approach":[57],"examines":[59],"both":[60,95],"audio":[61,76,134],"video":[63],"data":[64,77,135],"simultaneously.":[65],"While":[66],"an":[67],"EfficientNetB0-based":[68],"feature":[69],"extractor":[70],"used":[72],"image":[74,132],"data,":[75],"converted":[79],"into":[80],"Mel":[81],"spectrograms":[82],"analyzed":[84],"with":[85,115],"convolutional":[87],"neural":[88],"network":[89],"(CNN).":[90],"features":[92],"obtained":[93],"from":[94],"modalities":[96],"are":[97],"integrated":[98],"by":[99],"fusion":[101],"method.":[102],"proposed":[104],"system":[105],"trained":[107],"on":[108],"DFDC":[110],"(Deepfake":[111],"Detection":[112],"Challenge)":[113],"dataset":[114],"two-stage":[117],"training":[118],"process":[119],"(transfer":[120],"fine-tuning).":[123],"shows":[126],"combined":[129],"use":[130],"can":[136],"success":[139],"learning-based":[142],"forgery":[143],"detection":[144],"systems.":[145]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}