{"id":"https://openalex.org/W7138269006","doi":"https://doi.org/10.1609/aaai.v40i5.37334","title":"Improving Deepfake Detection with Reinforcement Learning-Based Adaptive Data Augmentation","display_name":"Improving Deepfake Detection with Reinforcement Learning-Based Adaptive Data Augmentation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138269006","doi":"https://doi.org/10.1609/aaai.v40i5.37334"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i5.37334","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37334","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37334/41296","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37334/41296","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129688051","display_name":"Yuxuan Chou","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Chou","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University\nPengcheng Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University\nPengcheng Laboratory","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I3131625388"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129668447","display_name":"Tao Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Yu","raw_affiliation_strings":["Institute of automation, Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of automation, Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129686154","display_name":"Wen Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Huang","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129674582","display_name":"ZhangYuHeng","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"ZhangYuHeng","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129742869","display_name":"Tao Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Dai","raw_affiliation_strings":["College of Computer Science and Software Engineering, Shenzhen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Software Engineering, Shenzhen University","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129641620","display_name":"Shu-Tao Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu-Tao Xia","raw_affiliation_strings":["Tsinghua Shenzhen International Graduate School, Tsinghua University\nPengcheng Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua Shenzhen International Graduate School, Tsinghua University\nPengcheng Laboratory","institution_ids":["https://openalex.org/I4210114105","https://openalex.org/I3131625388"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"5","first_page":"3381","last_page":"3389"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9634000062942505,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9634000062942505,"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/T11448","display_name":"Face recognition and analysis","score":0.008500000461935997,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.00800000037997961,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7307000160217285},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.6779999732971191},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5480999946594238},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5263000130653381},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.40950000286102295},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.39809998869895935},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.3781999945640564},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.36719998717308044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7874000072479248},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7307000160217285},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6779999732971191},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5985000133514404},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5480999946594238},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5263000130653381},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4794999957084656},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.40950000286102295},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.39809998869895935},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.36719998717308044},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i5.37334","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37334","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37334/41296","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/37334","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i5.37334","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i5.37334","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37334/41296","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138269006.pdf","grobid_xml":"https://content.openalex.org/works/W7138269006.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"generalization":[1,225],"capability":[2],"of":[3,52,67,124,146,247],"deepfake":[4],"detectors":[5],"is":[6,143,183],"crucial":[7],"for":[8],"real-world":[9,68],"applications.":[10],"Data":[11,97],"augmentation":[12,35,45,158,165,229],"to":[13,24,106,114,133,140,175,185,215,254],"generate":[14],"synthetic":[15,228],"fake":[16],"faces":[17],"has":[18],"served":[19],"as":[20,72],"an":[21,160],"effective":[22],"strategy":[23],"enhance":[25],"generalization.":[26],"Interestingly,":[27],"current":[28,136],"state-of-the-art":[29,255],"(SoTA)":[30],"methods":[31,62,256],"rely":[32],"on":[33,168,217,257],"fixed":[34,86],"strategies,":[36],"raising":[37],"a":[38,42,99,121],"fundamental":[39],"question:":[40],"Can":[41],"single":[43],"static":[44],"approach":[46,142],"suffice,":[47],"or":[48],"does":[49],"the":[50,64,104,134,144,156,169,180,213,232,240,245,248],"diversity":[51],"forgery":[53,69,110,125,193],"features":[54,111],"necessitate":[55],"dynamic":[56],"strategies?":[57],"We":[58],"argue":[59],"that":[60,102,239],"existing":[61],"overlook":[63],"evolving":[65],"complexity":[66],"patterns,":[70],"such":[71],"facial":[73],"warping,":[74],"expression":[75],"manipulation,":[76],"and":[77,127,150,211],"compression":[78],"artifacts,":[79],"which":[80,203],"cannot":[81],"be":[82],"fully":[83],"simulated":[84],"by":[85,199,207,226],"policies.":[87],"To":[88,153],"bridge":[89],"this":[90],"gap,":[91],"we":[92],"propose":[93],"CRDA":[94,116],"(Curriculum":[95],"Reinforcement-Learning":[96],"Augmentation),":[98],"novel":[100],"framework":[101],"guides":[103],"detector":[105],"progressively":[107],"master":[108],"multi-domain":[109],"from":[112,231],"simple":[113],"complex.":[115],"synthesizes":[117],"augmented":[118],"samples":[119,131],"using":[120],"configurable":[122],"pool":[123],"operations":[126],"dynamically":[128,163],"generates":[129],"adversarial":[130],"tailored":[132],"detector\u2019s":[135,170],"learning":[137,148],"state.":[138],"Key":[139],"our":[141],"integration":[145,222],"reinforcement":[147],"(RL)":[149],"causal":[151,200],"inference.":[152],"efficiently":[154],"explore":[155],"vast":[157],"space,":[159],"RL":[161],"agent":[162],"selects":[164],"actions":[166],"based":[167],"performance,":[171],"ensuring":[172],"continuous":[173],"adaptation":[174],"increasingly":[176],"challenging":[177],"forgeries.":[178],"Simultaneously,":[179],"agent\u2019s":[181],"output":[182],"designed":[184],"introduce":[186],"variations":[187,196],"in":[188],"action":[189],"spaces,":[190],"generating":[191],"heterogeneous":[192],"patterns.":[194],"These":[195],"are":[197],"guided":[198],"inference":[201],"theory,":[202],"mitigates":[204],"spurious":[205],"correlations":[206],"suppressing":[208],"task-irrelevant":[209],"biases":[210],"enforcing":[212],"model":[214],"focus":[216],"causally":[218],"invariant":[219],"features.":[220],"This":[221],"ensures":[223],"robust":[224],"decoupling":[227],"patterns":[230],"model\u2019s":[233],"learned":[234],"representations.":[235],"Extensive":[236],"experiments":[237],"demonstrate":[238],"proposed":[241],"method":[242],"significantly":[243],"improves":[244],"generalizability":[246],"detector,":[249],"achieving":[250],"superior":[251],"performance":[252],"compared":[253],"multiple":[258],"cross-domain":[259],"datasets.":[260]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}