{"id":"https://openalex.org/W4408354915","doi":"https://doi.org/10.1109/icassp49660.2025.10889125","title":"MIFAE-Forensics: Masked Image-Frequency AutoEncoder for DeepFake Detection","display_name":"MIFAE-Forensics: Masked Image-Frequency AutoEncoder for DeepFake Detection","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354915","doi":"https://doi.org/10.1109/icassp49660.2025.10889125"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889125","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5058079505","display_name":"Hanyi Wang","orcid":"https://orcid.org/0000-0002-5542-165X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanyi Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100623100","display_name":"Zihan Liu","orcid":"https://orcid.org/0000-0002-0874-0682"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Liu","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114430030","display_name":"Shilin Wang","orcid":"https://orcid.org/0009-0008-5171-9505"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilin Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,School of Electronic Information and Electrical Engineering","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.974399983882904,"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":0.974399983882904,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9174000024795532,"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/autoencoder","display_name":"Autoencoder","score":0.7876399159431458},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6974050998687744},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5899397134780884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5247145891189575},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4361620843410492},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3367805778980255},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.13903898000717163}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7876399159431458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6974050998687744},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5899397134780884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5247145891189575},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4361620843410492},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3367805778980255},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.13903898000717163}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889125","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889125","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.5600000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W2325939864","https://openalex.org/W2962858109","https://openalex.org/W2963720850","https://openalex.org/W2982058372","https://openalex.org/W3034196597","https://openalex.org/W3034301684","https://openalex.org/W3034552680","https://openalex.org/W3034713808","https://openalex.org/W3034864980","https://openalex.org/W3034900344","https://openalex.org/W3092879151","https://openalex.org/W3094728142","https://openalex.org/W3158353280","https://openalex.org/W3173317327","https://openalex.org/W3174508664","https://openalex.org/W3174656926","https://openalex.org/W3176241004","https://openalex.org/W3183999072","https://openalex.org/W3203605797","https://openalex.org/W4200635057","https://openalex.org/W4214680478","https://openalex.org/W4312388562","https://openalex.org/W4312753047","https://openalex.org/W4313127140","https://openalex.org/W4313156423","https://openalex.org/W4386065949","https://openalex.org/W4386076635","https://openalex.org/W4386076638","https://openalex.org/W6756046522","https://openalex.org/W6762480454","https://openalex.org/W6762718338","https://openalex.org/W6784333009","https://openalex.org/W6784810453","https://openalex.org/W6838657836"],"related_works":["https://openalex.org/W4220775285","https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747"],"abstract_inverted_index":{"With":[0],"continuously":[1],"evolving":[2],"generative":[3],"models":[4],"and":[5,23,100,107,120,134,175],"increasingly":[6],"diverse":[7],"face":[8],"forgery":[9,30,69,152],"products,":[10],"there":[11],"is":[12,50,58,146,202],"a":[13,89,132,193],"growing":[14],"demand":[15],"for":[16,139],"DeepFake":[17,140,197],"detectors":[18],"with":[19,155],"stronger":[20],"generalization":[21],"ability":[22,170],"robustness.":[24],"Previous":[25],"works":[26],"mainly":[27],"capture":[28,113],"method-specific":[29],"artifacts":[31],"in":[32,117,123,159],"the":[33,129,143,165,169],"training":[34],"set,":[35],"thus":[36],"failing":[37],"to":[38,41,61,112,149,171,178],"generalize":[39],"well":[40],"unseen":[42],"manipulations.":[43],"In":[44],"this":[45],"paper,":[46],"our":[47],"key":[48],"insight":[49],"that":[51,164],"exploring":[52],"common":[53],"characteristics":[54],"of":[55,74,131,196],"natural":[56,114],"faces":[57,158,174],"more":[59],"ideal":[60],"alleviate":[62],"overfitting":[63],"rather":[64],"than":[65],"relying":[66],"on":[67,182,192],"specific":[68],"clues,":[70],"as":[71],"all":[72],"sorts":[73],"manipulated":[75],"images":[76],"have":[77],"intrinsic":[78],"distributional":[79],"differences":[80],"from":[81,103],"those":[82],"captured":[83],"by":[84],"cameras.":[85],"Hence,":[86],"we":[87],"propose":[88],"two-stage":[90],"method,":[91],"termed":[92],"MIFAE-Forensics.":[93],"Specifically,":[94],"it":[95,177],"reconstructs":[96],"both":[97],"facial":[98,105,115,136],"semantics":[99],"local":[101],"details":[102,122],"masked":[104],"regions":[106],"high-frequency":[108,121],"components,":[109],"respectively,":[110],"aiming":[111],"consistency":[116],"spatial":[118,160],"domain":[119,125],"frequency":[124],"simultaneously.":[126],"This":[127],"facilitates":[128],"learning":[130],"robust":[133],"transferable":[135],"representation":[137],"specialized":[138],"detection.":[141],"Subsequently,":[142],"pre-trained":[144],"model":[145,172],"further":[147],"fine-tuned":[148],"perform":[150],"binary":[151],"classification":[153],"along":[154],"reconstructing":[156],"real":[157,173],"domain,":[161],"which":[162],"ensures":[163],"detector":[166],"can":[167],"maintain":[168],"encourages":[176],"make":[179],"decisions":[180],"based":[181],"reconstruction":[183],"discrepancies.":[184],"Extensive":[185],"experiments":[186],"show":[187],"superior":[188],"results":[189],"over":[190],"state-of-the-arts":[191],"wide":[194],"range":[195],"detection":[198],"benchmarks.":[199],"Our":[200],"code":[201],"available":[203],"at":[204],"https://github.com/Mark-Dou/Forensics.":[205]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
