{"id":"https://openalex.org/W4414945311","doi":"https://doi.org/10.1145/3746265.3759661","title":"MGGA: Universal Perturbations against Deepfake via Multiple Model-based Gradient-Guided Feature Layer Attack","display_name":"MGGA: Universal Perturbations against Deepfake via Multiple Model-based Gradient-Guided Feature Layer Attack","publication_year":2025,"publication_date":"2025-10-08","ids":{"openalex":"https://openalex.org/W4414945311","doi":"https://doi.org/10.1145/3746265.3759661"},"language":"en","primary_location":{"id":"doi:10.1145/3746265.3759661","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746265.3759661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st on Deepfake Forensics Workshop: Detection, Attribution, Recognition, and Adversarial Challenges in the Era of AI-Generated Media","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/A5110845196","display_name":"Zhi Cao","orcid":"https://orcid.org/0009-0007-6130-8366"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhi Cao","raw_affiliation_strings":["School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100741750","display_name":"Zhongyuan Wang","orcid":"https://orcid.org/0000-0002-9796-488X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongyuan Wang","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614000","display_name":"Run Wang","orcid":"https://orcid.org/0000-0002-2842-5137"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Run Wang","raw_affiliation_strings":["School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Wuhan University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102859655","display_name":"Yuhong Yang","orcid":"https://orcid.org/0000-0003-3001-7957"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhong Yang","raw_affiliation_strings":["School of Computer Science, Wuhan University, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Wuhan University, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075773112","display_name":"Feng Tian","orcid":"https://orcid.org/0000-0002-7687-3671"},"institutions":[{"id":"https://openalex.org/I4210159968","display_name":"Duke Kunshan University","ror":"https://ror.org/04sr5ys16","country_code":"CN","type":"education","lineage":["https://openalex.org/I170897317","https://openalex.org/I37461747","https://openalex.org/I4210159968"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Tian","raw_affiliation_strings":["Division of Natural and Applied Sciences, Duke Kunshan University, Kunshan, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Division of Natural and Applied Sciences, Duke Kunshan University, Kunshan, Jiangsu, China","institution_ids":["https://openalex.org/I4210159968"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104128998","display_name":"Gang Wu","orcid":"https://orcid.org/0009-0003-9953-3543"},"institutions":[{"id":"https://openalex.org/I3129293551","display_name":"Tarim University","ror":"https://ror.org/05202v862","country_code":"CN","type":"education","lineage":["https://openalex.org/I3129293551"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Wu","raw_affiliation_strings":["College of Cyber Security, Tarim University, Alar, Xinjiang, China"],"affiliations":[{"raw_affiliation_string":"College of Cyber Security, Tarim University, Alar, Xinjiang, China","institution_ids":["https://openalex.org/I3129293551"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101447641","display_name":"Atsushi Suzuki","orcid":"https://orcid.org/0000-0002-9447-7146"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Atsushi Suzuki","raw_affiliation_strings":["Department of Mathematics, The University of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, The University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5110845196"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14362385,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"82"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998999834060669,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9958000183105469,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.9950000047683716,"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/transferability","display_name":"Transferability","score":0.8507999777793884},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.8266000151634216},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.598800003528595},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5282999873161316},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5164999961853027},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3849000036716461}],"concepts":[{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.8507999777793884},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8266000151634216},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.715399980545044},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.598800003528595},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5282999873161316},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5164999961853027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4740999937057495},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3955000042915344},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39169999957084656},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32440000772476196},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30970001220703125},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.2581000030040741},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2508000135421753},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746265.3759661","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746265.3759661","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1st on Deepfake Forensics Workshop: Detection, Attribution, Recognition, and Adversarial Challenges in the Era of AI-Generated Media","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1017878125","display_name":null,"funder_award_id":"62371350,62171326,62202340","funder_id":"https://openalex.org/F4320334062","funder_display_name":"National Natural Science Foundation of China-Liaoning Joint Fund"},{"id":"https://openalex.org/G4740095446","display_name":null,"funder_award_id":"2042025kf0054","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6976618703","display_name":null,"funder_award_id":"2025AFB455","funder_id":"https://openalex.org/F4320322186","funder_display_name":"Natural Science Foundation of Hubei Province"}],"funders":[{"id":"https://openalex.org/F4320322186","display_name":"Natural Science Foundation of Hubei Province","ror":null},{"id":"https://openalex.org/F4320334062","display_name":"National Natural Science Foundation of China-Liaoning Joint Fund","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1834627138","https://openalex.org/W2508457857","https://openalex.org/W2774644650","https://openalex.org/W2883861033","https://openalex.org/W2891145043","https://openalex.org/W2895250390","https://openalex.org/W2896078964","https://openalex.org/W2911424785","https://openalex.org/W2914304175","https://openalex.org/W2924785549","https://openalex.org/W2962793481","https://openalex.org/W2963542245","https://openalex.org/W2963626105","https://openalex.org/W2963767194","https://openalex.org/W2982058372","https://openalex.org/W3028481464","https://openalex.org/W3035574324","https://openalex.org/W3092997524","https://openalex.org/W3108854358","https://openalex.org/W3127084502","https://openalex.org/W3127807678","https://openalex.org/W3164572690","https://openalex.org/W3175032500","https://openalex.org/W3175906703","https://openalex.org/W3176406820","https://openalex.org/W3182270175","https://openalex.org/W3186991201","https://openalex.org/W3196878101","https://openalex.org/W3201409833","https://openalex.org/W4293580221","https://openalex.org/W4297775537","https://openalex.org/W4297814571","https://openalex.org/W4308945593","https://openalex.org/W4310732279","https://openalex.org/W4312575110","https://openalex.org/W4312716239","https://openalex.org/W4386075893","https://openalex.org/W4386942368","https://openalex.org/W4388937529","https://openalex.org/W4393002335","https://openalex.org/W4402753991","https://openalex.org/W4402997546"],"related_works":[],"abstract_inverted_index":{"The":[0],"application":[1],"of":[2,119,137],"deepfake":[3],"models":[4,98,140],"for":[5],"image":[6],"editing":[7],"has":[8],"become":[9],"increasingly":[10],"popular,":[11],"yet":[12],"their":[13,36],"malicious":[14],"use":[15],"poses":[16],"significant":[17],"risks.":[18],"Recent":[19],"studies":[20],"using":[21],"active":[22],"defense":[23],"mechanisms":[24],"achieve":[25],"satisfactory":[26],"results":[27],"while":[28],"maintaining":[29],"the":[30,78,84,112,117,129,135],"forgery":[31,93,139],"model":[32],"and":[33,107],"dataset,":[34],"whereas":[35],"performance":[37],"declines":[38],"significantly":[39],"when":[40],"encountering":[41],"out-of-distribution":[42],"samples.":[43],"To":[44],"address":[45],"this":[46],"issue,":[47],"we":[48,65,110],"propose":[49],"a":[50],"method":[51],"that":[52,64,128],"utilizes":[53],"gradient":[54],"information":[55],"to":[56,115,122],"guide":[57],"attacks":[58],"on":[59,68,101],"intermediate":[60],"feature":[61],"layers":[62],"so":[63],"can":[66],"focus":[67],"data's":[69],"intrinsic":[70],"features":[71],"rather":[72],"than":[73],"model-specific":[74],"training":[75],"features.":[76],"When":[77],"adversarial":[79,120],"perturbation":[80,121,132],"is":[81],"correlated":[82],"with":[83],"data,":[85],"it":[86],"remains":[87],"effective":[88],"in":[89],"defending":[90],"against":[91],"multiple":[92],"models,":[94],"even":[95],"though":[96],"these":[97],"are":[99],"based":[100],"different":[102,142],"infrastructures":[103],"such":[104],"as":[105],"GAN":[106],"DM.":[108],"Furthermore,":[109],"incorporate":[111],"mixup":[113],"technique":[114],"enhance":[116],"transferability":[118],"data.":[123],"Our":[124],"extensive":[125],"experiments":[126],"show":[127],"proposed":[130],"universal":[131],"successfully":[133],"distorts":[134],"outputs":[136],"various":[138],"across":[141],"datasets.":[143]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-10-10T00:00:00"}