{"id":"https://openalex.org/W7162430558","doi":"https://doi.org/10.48550/arxiv.2605.24906","title":"Where Detectors Fail: Probing Generative Space for Generalizable AI-Generated Image Detection","display_name":"Where Detectors Fail: Probing Generative Space for Generalizable AI-Generated Image Detection","publication_year":2026,"publication_date":"2026-05-24","ids":{"openalex":"https://openalex.org/W7162430558","doi":"https://doi.org/10.48550/arxiv.2605.24906"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.24906","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24906","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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.24906","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048173508","display_name":"Zijie Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Zijie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049740771","display_name":"Weijie Tu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tu, Weijie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137001449","display_name":"Yao Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137038904","display_name":"Weijian Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Weijian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137060870","display_name":"Liang Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137006856","display_name":"Pengxu Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Pengxu","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":0.6546000242233276,"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":0.6546000242233276,"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":0.10459999740123749,"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":0.04879999905824661,"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":0.8047999739646912},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6823999881744385},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.6789000034332275},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5896999835968018},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5867000222206116},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5479000210762024},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4456000030040741},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.41780000925064087}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8047999739646912},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390999794006348},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6823999881744385},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.6789000034332275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6599000096321106},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5896999835968018},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5867000222206116},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5479000210762024},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4408000111579895},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.41780000925064087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3937999904155731},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3353999853134155},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.290800005197525},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2669000029563904},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.24906","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24906","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.24906","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.24906","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":"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Detecting":[0],"AI-generated":[1],"images":[2],"(AIGI)":[3],"remains":[4],"challenging":[5,99],"because":[6],"detectors":[7],"often":[8],"fail":[9],"to":[10,12,122,135,153,167],"generalize":[11],"unseen":[13,168],"generators.":[14],"Although":[15],"existing":[16],"methods":[17],"are":[18,73,133,143,151,180],"trained":[19],"on":[20,52],"large":[21],"datasets,":[22],"their":[23],"performance":[24],"still":[25],"degrades":[26],"when":[27],"generation":[28],"settings":[29],"change,":[30],"indicating":[31],"that":[32,39,57,92,132,142,163],"data":[33,113,147],"scale":[34],"alone":[35],"is":[36,47],"insufficient":[37],"and":[38,66,150,178],"limited":[40],"coverage":[41],"of":[42,71,101,106],"generative":[43,53,103],"variations":[44],"during":[45],"training":[46],"a":[48,90,111,120],"key":[49],"factor.":[50],"Studies":[51],"model":[54],"editing":[55],"show":[56],"small":[58],"changes":[59],"in":[60,171],"internal":[61],"representations":[62],"can":[63],"produce":[64],"diverse":[65],"meaningful":[67],"image":[68],"variations,":[69],"many":[70],"which":[72],"not":[74],"explored":[75],"under":[76,145],"standard":[77,146],"sampling.":[78],"Leveraging":[79],"this":[80],"insight,":[81],"we":[82],"propose":[83],"PROBE":[84,115,164],"(Probing":[85],"Robustness":[86],"via":[87],"Boundary":[88],"Exploration),":[89],"framework":[91],"improves":[93],"detector":[94,118],"generalization":[95,166],"by":[96],"actively":[97],"exploring":[98],"regions":[100],"the":[102,108,117,124,155],"process.":[104],"Instead":[105],"treating":[107],"generator":[109,125],"as":[110,119],"fixed":[112],"source,":[114],"uses":[116],"critic":[121],"steer":[123],"through":[126],"manifold-level":[127],"modifications,":[128],"producing":[129],"realistic":[130],"samples":[131,138],"difficult":[134],"classify.":[136],"These":[137],"expose":[139],"failure":[140],"cases":[141],"uncommon":[144],"sampling":[148],"strategies":[149],"used":[152],"refine":[154],"detector.":[156],"Experimental":[157],"results":[158],"across":[159],"multiple":[160],"benchmarks":[161],"indicate":[162],"enhances":[165],"generators,":[169],"resulting":[170],"more":[172],"generalizable":[173],"AIGI":[174],"detection":[175],"performance.":[176],"Code":[177],"models":[179],"available":[181],"at":[182],"https://github.com/Amamiya-C/PROBE-AIGI-Detection":[183]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-27T00:00:00"}