{"id":"https://openalex.org/W7225320371","doi":"https://doi.org/10.17148/ijarcce.2026.151159","title":"Training Data Diversity and Distribution Shift in AI-Generated Image Detection: An Empirical Study","display_name":"Training Data Diversity and Distribution Shift in AI-Generated Image Detection: An Empirical Study","publication_year":2026,"publication_date":"2026-11-05","ids":{"openalex":"https://openalex.org/W7225320371","doi":"https://doi.org/10.17148/ijarcce.2026.151159"},"language":"en","primary_location":{"id":"doi:10.17148/ijarcce.2026.151159","doi":"https://doi.org/10.17148/ijarcce.2026.151159","is_oa":true,"landing_page_url":"https://doi.org/10.17148/ijarcce.2026.151159","pdf_url":"https://doi.org/10.17148/ijarcce.2026.151159","source":{"id":"https://openalex.org/S4210187166","display_name":"IJARCCE","issn_l":"2278-1021","issn":["2278-1021","2319-5940"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IJARCCE","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.17148/ijarcce.2026.151159","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160835097","display_name":"E Niranjan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E Niranjan","raw_affiliation_strings":["Student,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Student,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160780707","display_name":"Arushi A","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Arushi A","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160788796","display_name":"Deesha S Chajer","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deesha S Chajer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5013729632","display_name":"S Niveditha","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Niveditha S","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"11","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":1.0,"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":1.0,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":9.999999747378752e-05,"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":0.0,"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/ai-generated-image-detection","display_name":"AI-generated image detection","score":0.9810000061988831},{"id":"https://openalex.org/keywords/distribution-shift","display_name":"distribution shift","score":0.7609999775886536},{"id":"https://openalex.org/keywords/training-data-diversity","display_name":"training data diversity","score":0.8669999837875366},{"id":"https://openalex.org/keywords/generative-ai","display_name":"generative AI","score":0.5640000104904175},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.6499999761581421},{"id":"https://openalex.org/keywords/resnet-18","display_name":"ResNet-18","score":0.6209999918937683},{"id":"https://openalex.org/keywords/efficientnet-b3","display_name":"EfficientNetB3","score":0.9959999918937683},{"id":"https://openalex.org/keywords/threshold-calibration","display_name":"threshold calibration","score":0.6650000214576721}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6262999773025513},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5751000046730042},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.545199990272522},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.49810001254081726},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.4855000078678131},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4805999994277954},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4586000144481659},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45579999685287476},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.43630000948905945},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.4214000105857849},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.41819998621940613},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C83248878","wikidata":"https://www.wikidata.org/wiki/Q344000","display_name":"Active appearance model","level":3,"score":0.37389999628067017},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3422999978065491},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.33889999985694885},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3330000042915344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3285999894142151},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.30329999327659607},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28769999742507935},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27149999141693115},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.17148/ijarcce.2026.151159","doi":"https://doi.org/10.17148/ijarcce.2026.151159","is_oa":true,"landing_page_url":"https://doi.org/10.17148/ijarcce.2026.151159","pdf_url":"https://doi.org/10.17148/ijarcce.2026.151159","source":{"id":"https://openalex.org/S4210187166","display_name":"IJARCCE","issn_l":"2278-1021","issn":["2278-1021","2319-5940"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IJARCCE","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.17148/ijarcce.2026.151159","doi":"https://doi.org/10.17148/ijarcce.2026.151159","is_oa":true,"landing_page_url":"https://doi.org/10.17148/ijarcce.2026.151159","pdf_url":"https://doi.org/10.17148/ijarcce.2026.151159","source":{"id":"https://openalex.org/S4210187166","display_name":"IJARCCE","issn_l":"2278-1021","issn":["2278-1021","2319-5940"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IJARCCE","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225320371.pdf","grobid_xml":"https://content.openalex.org/works/W7225320371.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W4389370799","https://openalex.org/W7118682676","https://openalex.org/W7133207051"],"related_works":["https://openalex.org/W7138134961","https://openalex.org/W4413155783","https://openalex.org/W4410706528","https://openalex.org/W7166321509","https://openalex.org/W7133348166","https://openalex.org/W7216182481","https://openalex.org/W7133207051","https://openalex.org/W4407684102","https://openalex.org/W7162430558","https://openalex.org/W4402217224"],"abstract_inverted_index":{"The":[0],"proliferation":[1],"of":[2,18,46,86,186],"high-fidelity":[3],"generative":[4],"models":[5,118],"such":[6],"as":[7],"Stable":[8],"Diffusion,":[9],"DALL-E,":[10],"MidJourney,":[11],"and":[12,56,75,79,91,122,124,147,160,162,169],"Gemini":[13],"has":[14],"made":[15],"automated":[16],"detection":[17],"AI-generated":[19],"images":[20,62,87,103],"an":[21,43,99],"increasingly":[22],"important":[23],"research":[24],"problem.While":[25],"many":[26],"published":[27],"detectors":[28],"report":[29],"high":[30],"in-domain":[31],"accuracy,":[32],"their":[33],"performance":[34],"under":[35],"distribution":[36],"shift":[37],"is":[38],"often":[39],"overlooked.This":[40],"paper":[41],"presents":[42],"empirical":[44],"study":[45],"binary":[47],"real-versus-AI":[48],"image":[49],"classifiers,":[50],"examining":[51],"how":[52],"training":[53,167],"data":[54,73,187],"composition":[55],"architecture":[57],"choice":[58,197],"affect":[59],"accuracy":[60],"on":[61,71,81,134],"from":[63,88,188],"sources":[64,146,191],"not":[65],"seen":[66],"during":[67],"training.Models":[68],"trained":[69,97],"only":[70],"public":[72,150],"(ResNet18":[74],"EfficientNet-B3)":[76],"reached":[77,104],"53.33%":[78],"61.67%":[80],"a":[82,95,135,141,183],"60-image":[83],"held-out":[84],"set":[85],"web-based":[89],"generators":[90],"personal":[92],"photographs,":[93],"whereas":[94],"ResNet18":[96,133],"with":[98],"additional":[100],"360":[101],"self-collected":[102],"75.00%,":[105],"rising":[106],"to":[107],"81.67%":[108],"after":[109],"threshold":[110],"calibration.On":[111],"unseen":[112],"Tiny-GenImage":[113],"samples":[114],"(n=800)":[115],"the":[116,125,131,144,148,152,163,189,196],"three":[117],"scored":[119,128],"between":[120,143,198],"72.12%":[121],"74.75%,":[123],"data-augmented":[126],"model":[127,176],"lower":[129],"than":[130,195],"public-only":[132],"2,000image":[136],"slice":[137],"(68.85%":[138],"vs.":[139],"72.60%),indicating":[140],"trade-off":[142],"added":[145],"original":[149],"distribution.Because":[151],"two":[153,200],"architectures":[154],"have":[155],"near-identical":[156],"parameter":[157],"counts":[158],"(11.18M":[159],"10.70M)":[161],"runs":[164],"differ":[165],"in":[166],"volume":[168],"schedule,":[170],"we":[171],"draw":[172],"no":[173],"conclusion":[174],"about":[175],"capacity.The":[177],"results":[178],"suggest":[179],"that":[180],"adding":[181],"even":[182],"small":[184],"amount":[185],"target":[190],"can":[192],"matter":[193],"more":[194],"these":[199],"architectures.":[201]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-11-06T00:00:00"}