{"id":"https://openalex.org/W7128721813","doi":"https://doi.org/10.48550/arxiv.2602.10546","title":"RealHD: A High-Quality Dataset for Robust Detection of State-of-the-Art AI-Generated Images","display_name":"RealHD: A High-Quality Dataset for Robust Detection of State-of-the-Art AI-Generated Images","publication_year":2026,"publication_date":"2026-02-11","ids":{"openalex":"https://openalex.org/W7128721813","doi":"https://doi.org/10.48550/arxiv.2602.10546"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.10546","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.10546","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2602.10546","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125376903","display_name":"Hanzhe Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Hanzhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125697724","display_name":"Yun Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Yun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049686021","display_name":"Jintao Rong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rong, Jintao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125701706","display_name":"Qi Xuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuan, Qi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125764327","display_name":"Chen Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Chen","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":0.5394999980926514,"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":0.5394999980926514,"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":0.2872999906539917,"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":0.03550000116229057,"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/robustness","display_name":"Robustness (evolution)","score":0.63919997215271},{"id":"https://openalex.org/keywords/inpainting","display_name":"Inpainting","score":0.4964999854564667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.491100013256073},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4278999865055084},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.3971000015735626},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3878999948501587},{"id":"https://openalex.org/keywords/digital-image","display_name":"Digital image","score":0.3878999948501587},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3700999915599823}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7936999797821045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.715399980545044},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.63919997215271},{"id":"https://openalex.org/C11727466","wikidata":"https://www.wikidata.org/wiki/Q1628157","display_name":"Inpainting","level":3,"score":0.4964999854564667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43650001287460327},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4278999865055084},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.3971000015735626},{"id":"https://openalex.org/C42781572","wikidata":"https://www.wikidata.org/wiki/Q1250322","display_name":"Digital image","level":4,"score":0.3878999948501587},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3700999915599823},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.303600013256073},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2879999876022339},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2775999903678894},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C193828747","wikidata":"https://www.wikidata.org/wiki/Q864118","display_name":"Binary image","level":4,"score":0.2632000148296356},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.10546","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.10546","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2602.10546","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.10546","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,90,235],"rapid":[1],"advancement":[2],"of":[3,12,175,203],"generative":[4],"AI":[5],"has":[6],"raised":[7],"concerns":[8],"about":[9],"the":[10,173,196],"authenticity":[11],"digital":[13],"images,":[14],"as":[15,160],"highly":[16],"realistic":[17],"fake":[18],"images":[19,46,80,92,127],"can":[20],"now":[21],"be":[22],"generated":[23,91,116],"at":[24,43,243],"low":[25,57],"cost,":[26],"potentially":[27],"increasing":[28],"societal":[29],"risks.":[30],"In":[31],"response,":[32],"several":[33],"datasets":[34,52],"have":[35],"been":[36],"established":[37],"to":[38,132,142,171],"train":[39],"detection":[40,145,166,178,187],"models":[41,146,214],"aimed":[42],"distinguishing":[44],"AI-generated":[45,88,176],"from":[47,54],"real":[48,86],"ones.":[49],"However,":[50],"existing":[51,143],"suffer":[53],"limited":[55],"generalization,":[56,221],"image":[58,65,108,110,117,177,191,198],"quality,":[59],"overly":[60],"simple":[61],"prompts,":[62],"and":[63,87,112,124,222,237],"insufficient":[64],"diversity.":[66],"To":[67],"address":[68],"these":[69],"limitations,":[70],"we":[71,183],"propose":[72,184],"a":[73,161,185,229],"high-quality,":[74],"large-scale":[75],"dataset":[76,150,156,218,236],"comprising":[77],"over":[78,103],"730,000":[79],"across":[81],"multiple":[82],"categories,":[83],"including":[84,98],"both":[85],"images.":[89],"are":[93,240],"synthesized":[94],"via":[95],"state-of-the-art":[96],"methods,":[97],"text-to-image":[99],"generation":[100,122],"(guided":[101],"by":[102],"10,000":[104],"carefully":[105],"designed":[106],"prompts),":[107],"inpainting,":[109],"refinement,":[111],"face":[113],"swapping.":[114],"Each":[115],"is":[118],"annotated":[119],"with":[120],"its":[121],"method":[123,188,224],"category.":[125],"Inpainting":[126],"further":[128],"include":[129],"binary":[130],"masks":[131],"indicate":[133],"inpainted":[134],"regions,":[135],"providing":[136],"rich":[137],"metadata":[138],"for":[139,164,232],"analysis.":[140],"Compared":[141],"datasets,":[144],"trained":[147,215],"on":[148,190,216],"our":[149,217,223],"demonstrate":[151,212],"superior":[152],"generalization":[153],"capabilities.":[154],"Our":[155],"not":[157],"only":[158],"serves":[159],"strong":[162,220],"benchmark":[163],"evaluating":[165],"methods":[167],"but":[168],"also":[169],"contributes":[170],"advancing":[172],"robustness":[174],"techniques.":[179],"Building":[180],"upon":[181],"this,":[182],"lightweight":[186],"based":[189],"noise":[192,207],"entropy,":[193],"which":[194],"transforms":[195],"original":[197],"into":[199],"an":[200],"entropy":[201],"tensor":[202],"Non-Local":[204],"Means":[205],"(NLM)":[206],"before":[208],"classification.":[209],"Extensive":[210],"experiments":[211],"that":[213],"achieve":[219],"delivers":[225],"competitive":[226],"performance,":[227],"establishing":[228],"solid":[230],"baseline":[231],"future":[233],"research.":[234],"source":[238],"code":[239],"publicly":[241],"available":[242],"https://real-hd.github.io.":[244]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-02-13T00:00:00"}