{"id":"https://openalex.org/W7133348166","doi":"https://doi.org/10.48550/arxiv.2603.00717","title":"Leveraging Arbitrary Data Sources for AI-Generated Image Detection Without Sacrificing Generalization","display_name":"Leveraging Arbitrary Data Sources for AI-Generated Image Detection Without Sacrificing Generalization","publication_year":2026,"publication_date":"2026-02-28","ids":{"openalex":"https://openalex.org/W7133348166","doi":"https://doi.org/10.48550/arxiv.2603.00717"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.00717","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00717","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.2603.00717","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127884505","display_name":"Qinghui He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Qinghui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127899308","display_name":"Haifeng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Haifeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127965257","display_name":"Xiuli Bi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bi, Xiuli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128007263","display_name":"Bo Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Pun, Chi-Man","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pun, Chi-Man","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5127892321","display_name":"Bin Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Bin","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":0.9605000019073486,"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":0.9605000019073486,"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":0.016200000420212746,"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/T11094","display_name":"Face Recognition and Perception","score":0.003599999938160181,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.7279999852180481},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7228999733924866},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.717199981212616},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5950999855995178},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5408999919891357},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5250999927520752},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5069000124931335},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48330000042915344},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.46560001373291016}],"concepts":[{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.7279999852180481},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7228999733924866},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.717199981212616},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6995000243186951},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6450999975204468},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5950999855995178},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5408999919891357},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5250999927520752},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5069000124931335},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48330000042915344},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.46560001373291016},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46309998631477356},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44290000200271606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3978999853134155},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3635999858379364},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3433000147342682},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33149999380111694},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2669999897480011},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.26330000162124634},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.00717","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00717","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.2603.00717","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00717","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":[{"id":"https://metadata.un.org/sdg/10","score":0.6815558075904846,"display_name":"Reduced inequalities"}],"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],"accelerating":[1],"advancement":[2],"of":[3,105],"generative":[4,45,150],"models":[5],"has":[6],"introduced":[7],"new":[8],"challenges":[9],"for":[10],"detecting":[11],"AI-generated":[12],"images,":[13],"especially":[14],"in":[15,34,160,164],"real-world":[16],"scenarios":[17],"where":[18],"novel":[19],"generation":[20],"techniques":[21],"emerge":[22],"rapidly.":[23],"Existing":[24],"learning":[25],"paradigms":[26],"are":[27],"likely":[28],"to":[29,43,56],"make":[30],"classifiers":[31],"data-dependent,":[32],"resulting":[33],"narrow":[35],"decision":[36,117],"margins":[37],"and,":[38],"consequently,":[39],"limited":[40],"generalization":[41],"ability":[42],"unseen":[44,149],"models.":[46],"We":[47],"observe":[48],"that":[49,81,142],"both":[50],"real":[51,88,106],"and":[52,89,111,128,162],"generated":[53,90,109],"images":[54,91,107],"intend":[55],"form":[57],"clustered":[58],"low-dimensional":[59],"manifolds":[60],"within":[61],"high-level":[62],"feature":[63],"spaces":[64],"extracted":[65],"by":[66,92,155],"pre-trained":[67],"visual":[68],"encoders.":[69],"Building":[70],"on":[71,132],"this":[72],"observation,":[73],"we":[74],"propose":[75],"a":[76,94,114],"single-class":[77,100],"attribution":[78,96],"modeling":[79],"framework":[80],"first":[82],"amplifies":[83],"the":[84,120,130],"intrinsic":[85],"differences":[86],"between":[87],"constructing":[93],"compact":[95],"space":[97],"from":[98],"any":[99],"training":[101],"set,":[102],"either":[103],"composed":[104],"or":[108],"ones,":[110],"then":[112],"establishes":[113],"more":[115],"stable":[116],"boundary":[118],"upon":[119],"enlarged":[121],"separation.":[122],"This":[123],"process":[124],"enhances":[125],"class":[126],"distinction":[127],"mitigates":[129],"reliance":[131],"generator-specific":[133],"artifacts,":[134],"thereby":[135],"improving":[136],"cross-model":[137,165],"generalization.":[138,166],"Extensive":[139],"experiments":[140],"show":[141],"our":[143],"method":[144],"generalizes":[145],"well":[146],"across":[147],"various":[148],"models,":[151],"outperforming":[152],"existing":[153],"detectors":[154],"as":[156,158],"much":[157],"7.21%":[159],"accuracy":[161],"7.20%":[163]},"counts_by_year":[],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2026-03-04T00:00:00"}