{"id":"https://openalex.org/W7225254735","doi":"https://doi.org/10.48550/arxiv.2611.04111","title":"Generalizable AI-Generated Image Detection with Embedding-Space Explanations","display_name":"Generalizable AI-Generated Image Detection with Embedding-Space Explanations","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225254735","doi":"https://doi.org/10.48550/arxiv.2611.04111"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2611.04111","doi":"https://doi.org/10.48550/arxiv.2611.04111","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.04111","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2611.04111","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160672864","display_name":"Nikos Giakoumoglou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giakoumoglou, Nikos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116225207","display_name":"Paschalis Giakoumoglou","orcid":"https://orcid.org/0009-0008-4950-023X","observed_orcids":["https://orcid.org/0009-0008-4950-023X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giakoumoglou, Paschalis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028031376","display_name":"Tania Stathaki","orcid":"https://orcid.org/0000-0001-8578-0525","observed_orcids":["https://orcid.org/0000-0001-8578-0525"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stathaki, Tania","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5013616365","display_name":"Symeon Papadopoulos","orcid":"https://orcid.org/0000-0002-5441-7341","observed_orcids":["https://orcid.org/0000-0002-5441-7341"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Papadopoulos, Symeon","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/T12357","display_name":"Digital Media Forensic Detection","score":0.9980000257492065,"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":0.9980000257492065,"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":0.0010000000474974513,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.00019999999494757503,"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":0.9879999756813049},{"id":"https://openalex.org/keywords/explainable-ai","display_name":"explainable AI","score":0.6039999723434448},{"id":"https://openalex.org/keywords/dinov3","display_name":"DINOv3","score":0.8059999942779541},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.8579999804496765},{"id":"https://openalex.org/keywords/image-splicing-detection","display_name":"image splicing detection","score":0.38600000739097595}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7021999955177307},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7008000016212463},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6460000276565552},{"id":"https://openalex.org/C77660490","wikidata":"https://www.wikidata.org/wiki/Q244916","display_name":"Intermediate language","level":3,"score":0.5479999780654907},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48030000925064087},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4724000096321106},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4702000021934509},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4657999873161316},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.450300008058548},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.39629998803138733},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31940001249313354},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3125999867916107},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2939999997615814},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2930999994277954},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C2983812711","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Text recognition","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.27730000019073486},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27300000190734863}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2611.04111","doi":"https://doi.org/10.48550/arxiv.2611.04111","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.04111","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2611.04111","doi":"https://doi.org/10.48550/arxiv.2611.04111","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.04111","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416951179","https://openalex.org/W7203457219","https://openalex.org/W4416944614","https://openalex.org/W4416374043","https://openalex.org/W7202190129","https://openalex.org/W7172428937","https://openalex.org/W7203680892","https://openalex.org/W7165750806","https://openalex.org/W4417098972","https://openalex.org/W7140286693"],"abstract_inverted_index":{"AI-generated":[0],"images":[1,11],"have":[2],"reached":[3],"unprecedented":[4],"realism,":[5],"while":[6],"instruction-driven":[7],"AI":[8],"editors":[9],"re-synthesize":[10],"for":[12,70],"local":[13],"changes,":[14],"leaving":[15],"no":[16],"splice":[17],"boundary":[18],"to":[19,79,109],"localize.":[20],"Most":[21],"detectors":[22,48],"are":[23],"black":[24],"boxes":[25],"with":[26],"unverifiable":[27],"verdicts":[28],"and":[29,72,99,152],"generalize":[30,55],"poorly":[31],"because":[32],"adapting":[33],"a":[34,101,111,125],"backbone":[35],"on":[36,50,137,150,154],"the":[37,80,91,134],"detection":[38],"distribution":[39],"memorizes":[40],"generator-specific":[41],"fingerprints":[42],"that":[43,86,133],"quickly":[44],"become":[45],"obsolete.":[46],"Specialist":[47],"built":[49],"pure-vision":[51],"representations,":[52],"particularly":[53],"DINOv3,":[54],"well":[56],"across":[57,144],"generators,":[58,147],"but":[59],"explainable":[60],"methods":[61],"forgo":[62],"this":[63],"advantage:":[64],"jointly":[65],"training":[66,88],"one":[67],"multimodal":[68],"model":[69],"classification":[71],"language":[73,81],"generation":[74],"subjects":[75],"its":[76,107],"visual":[77,122],"representation":[78,108],"objective.":[82],"We":[83,93],"therefore":[84],"require":[85],"explanation":[87],"cannot":[89],"alter":[90],"verdict.":[92],"introduce":[94],"FOX,":[95],"which":[96],"first":[97],"builds":[98],"locks":[100],"specialist":[102],"DINOv3":[103],"detector,":[104],"then":[105],"uses":[106],"guide":[110],"lightweight":[112],"VLM":[113,135],"toward":[114],"forensic":[115],"explanation.":[116],"A":[117],"joint-embedding":[118],"predictor":[119],"maps":[120],"locked":[121],"evidence":[123],"into":[124],"frozen":[126],"text":[127],"encoder's":[128],"semantic":[129],"space,":[130],"producing":[131],"guidance":[132],"verbalizes":[136],"demand.":[138],"FOX":[139],"achieves":[140],"97.4":[141],"mean":[142],"AUC":[143],"14":[145],"unseen":[146],"69.8":[148],"BERTScore":[149],"XPlainVerse,":[151],"56.1":[153],"LOKI.":[155]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-05T00:00:00"}