{"id":"https://openalex.org/W7161237655","doi":"https://doi.org/10.48550/arxiv.2605.14486","title":"Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection","display_name":"Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection","publication_year":2026,"publication_date":"2026-05-14","ids":{"openalex":"https://openalex.org/W7161237655","doi":"https://doi.org/10.48550/arxiv.2605.14486"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.14486","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14486","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.14486","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136271096","display_name":"Yiheng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yiheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136267787","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0003-1434-1351"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040257967","display_name":"Zichang Tan","orcid":"https://orcid.org/0000-0002-8501-4123"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Zichang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136209228","display_name":"Gao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136223193","display_name":"Zhen Lei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei, Zhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136245118","display_name":"Wenhao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wenhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.4672999978065491,"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":0.4672999978065491,"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":0.25690001249313354,"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":0.1307000070810318,"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/artifact","display_name":"Artifact (error)","score":0.579200029373169},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.546999990940094},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5465999841690063},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5047000050544739},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4878000020980835},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.4772000014781952},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.42089998722076416},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.384799987077713},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.3828999996185303},{"id":"https://openalex.org/keywords/hallucinating","display_name":"Hallucinating","score":0.3684999942779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.796999990940094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7055000066757202},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.579200029373169},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.546999990940094},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5465999841690063},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5047000050544739},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4878000020980835},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.4772000014781952},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45159998536109924},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.42089998722076416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.3828999996185303},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36039999127388},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.32899999618530273},{"id":"https://openalex.org/C69744172","wikidata":"https://www.wikidata.org/wiki/Q860822","display_name":"Image fusion","level":3,"score":0.3095000088214874},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3018999993801117},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.29679998755455017},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.29260000586509705},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2524000108242035},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.14486","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14486","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.14486","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14486","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.6700546145439148,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"the":[1,120,142],"misuse":[2],"of":[3,114,141],"AI-generated":[4],"images":[5,80],"grows,":[6],"generalizable":[7],"image":[8,198],"detection":[9],"techniques":[10],"are":[11,239],"urgently":[12],"needed.":[13],"Recent":[14],"state-of-the-art":[15],"(SOTA)":[16],"methods":[17],"adopt":[18],"aligned":[19,82,110],"training":[20,131],"datasets":[21],"to":[22,31,40,119,153,183,211],"reduce":[23,159],"content,":[24,100],"size,":[25,101],"and":[26,46,62,102,125,158,204,218],"format":[27,103],"biases,":[28],"empowering":[29],"models":[30],"capture":[32,68],"robust":[33,215],"forgery":[34],"cues.":[35],"A":[36],"common":[37],"strategy":[38],"is":[39],"employ":[41],"reconstruction":[42],"techniques,":[43],"e.g.,":[44],"VAE":[45],"DDIM,":[47],"which":[48,65],"show":[49],"remarkable":[50],"results":[51,107,233],"in":[52,108],"diffusion-based":[53],"methods.":[54,75,224],"However,":[55,117],"such":[56,72],"reconstruction-based":[57,78,124],"approaches":[58],"typically":[59],"introduce":[60],"limited":[61],"homogeneous":[63],"artifacts,":[64],"cannot":[66],"fully":[67],"diverse":[69,84,203,236],"generative":[70,223],"patterns,":[71,86],"as":[73],"GAN-based":[74,90],"To":[76],"complement":[77],"fake":[79,96,115,127],"with":[81,179],"yet":[83],"artifact":[85,156,206],"we":[87,145],"propose":[88,146],"a":[89,147,171,180,213],"upsampling":[91],"approach":[92],"that":[93,208,228],"mimics":[94],"GAN-generated":[95,197],"patterns":[97,207],"while":[98,188],"preserving":[99],"alignment.":[104],"This":[105],"naturally":[106],"two":[109],"but":[111],"distinct":[112],"types":[113],"images.":[116],"due":[118],"domain":[121,137],"shift":[122],"between":[123],"upsampling-based":[126],"images,":[128],"direct":[129],"mixed":[130],"causes":[132],"suboptimal":[133],"results,":[134],"where":[135],"one":[136],"disrupts":[138],"feature":[139],"learning":[140],"other.":[143],"Accordingly,":[144],"Separate":[148],"Expert":[149],"Fusion":[150],"(SEF)":[151],"framework":[152],"extract":[154],"complementary":[155,205],"information":[157],"inter-domain":[160],"interference.":[161],"We":[162],"first":[163],"train":[164],"domain-specific":[165],"experts":[166],"via":[167],"LoRA":[168],"adaptation":[169],"on":[170],"frozen":[172],"foundational":[173],"model,":[174],"then":[175],"conduct":[176],"decoupled":[177],"fusion":[178],"gating":[181],"network":[182],"adaptively":[184],"combine":[185],"expert":[186],"features":[187],"retaining":[189],"their":[190],"specialized":[191],"knowledge.":[192],"Rather":[193],"than":[194],"merely":[195],"benefiting":[196],"detection,":[199],"this":[200],"design":[201],"introduces":[202],"enable":[209],"SEF":[210],"learn":[212],"more":[214],"decision":[216],"boundary":[217],"improve":[219],"generalization":[220],"across":[221,234],"broader":[222],"Extensive":[225],"experiments":[226],"demonstrate":[227],"our":[229],"method":[230],"yields":[231],"strong":[232],"13":[235],"benchmarks.":[237],"Codes":[238],"released":[240],"at:":[241],"https://github.com/liyih/SEF_AIGC_detection.":[242]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-16T00:00:00"}