{"id":"https://openalex.org/W7138041311","doi":"https://doi.org/10.48550/arxiv.2603.14220","title":"FIND: A Simple yet Effective Baseline for Diffusion-Generated Image Detection","display_name":"FIND: A Simple yet Effective Baseline for Diffusion-Generated Image Detection","publication_year":2026,"publication_date":"2026-03-15","ids":{"openalex":"https://openalex.org/W7138041311","doi":"https://doi.org/10.48550/arxiv.2603.14220"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.14220","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14220","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.14220","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129741902","display_name":"Jie Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129709525","display_name":"Yingying Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Yingying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129686890","display_name":"Chi Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Chi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129662942","display_name":"Jie Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129723727","display_name":"Lei Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129680659","display_name":"Jiayi Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Jiayi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"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/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.387800008058548,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.387800008058548,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.1257999986410141,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.10649999976158142,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7235999703407288},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.541100025177002},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.49810001254081726},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4652000069618225},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4410000145435333},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.42649999260902405},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.42419999837875366},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4169999957084656},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.37929999828338623}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7357000112533569},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7235999703407288},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6665999889373779},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.541100025177002},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.49810001254081726},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46129998564720154},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.42649999260902405},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.36000001430511475},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.2985999882221222},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2937999963760376},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27230000495910645},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.26809999346733093},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.257999986410141},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.14220","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14220","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.14220","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14220","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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7666539549827576}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0,184],"remarkable":[1],"realism":[2],"of":[3,161],"images":[4,27,61,120,154,157],"generated":[5],"by":[6,98,166,189],"diffusion":[7,35,48,208],"models":[8,209],"poses":[9],"critical":[10],"detection":[11],"challenges.":[12],"Current":[13],"methods":[14],"utilize":[15],"reconstruction":[16,30,42,97],"error":[17],"as":[18,128],"a":[19,57,85,91,214],"discriminative":[20,181],"feature,":[21],"exploiting":[22],"the":[23,101,133,138,151,175,179,192,204],"observation":[24],"that":[25,88,141,150],"real":[26,60,106,119,143,153],"exhibit":[28],"higher":[29],"errors":[31],"when":[32],"processed":[33],"through":[34],"models.":[36],"However,":[37],"these":[38,125],"approaches":[39],"require":[40],"costly":[41],"computations":[43],"and":[44,107,123,210,217],"depend":[45],"on":[46,137,191],"specific":[47],"models,":[49],"making":[50],"their":[51,159],"performance":[52,188],"highly":[53],"model-dependent.":[54],"We":[55,147],"identify":[56],"fundamental":[58],"difference:":[59],"are":[62],"more":[63],"difficult":[64],"to":[65,71,114,118,135,174,220],"fit":[66],"with":[67],"Gaussian":[68,116,162],"distributions":[69],"compared":[70],"synthetic":[72,108,145],"ones.":[73],"In":[74],"this":[75],"paper,":[76],"we":[77],"propose":[78],"Forgery":[79],"Identification":[80],"via":[81],"Noise":[82],"Disturbance":[83],"(FIND),":[84],"novel":[86],"method":[87],"requires":[89],"only":[90],"simple":[92],"binary":[93],"classifier.":[94],"It":[95],"eliminates":[96],"directly":[99],"targeting":[100],"core":[102],"distributional":[103],"difference":[104],"between":[105],"images.":[109,146],"Our":[110],"key":[111],"operation":[112],"is":[113],"add":[115],"noise":[117],"during":[121],"training":[122],"label":[124],"noisy":[126],"versions":[127],"synthetic.":[129],"This":[130],"step":[131],"allows":[132],"classifier":[134],"focus":[136],"statistical":[139],"patterns":[140],"distinguish":[142],"from":[144],"theoretically":[148],"prove":[149],"noise-augmented":[152],"resemble":[155],"diffusion-generated":[156,222],"in":[158],"ease":[160],"fitting.":[163],"Furthermore,":[164],"simply":[165],"adding":[167],"noise,":[168],"they":[169],"still":[170],"retain":[171],"visual":[172],"similarity":[173],"original":[176],"images,":[177],"highlighting":[178],"most":[180],"distribution-related":[182],"features.":[183],"proposed":[185],"FIND":[186],"improves":[187],"11.7%":[190],"GenImage":[193],"benchmark":[194],"while":[195],"running":[196],"126x":[197],"faster":[198],"than":[199],"existing":[200],"methods.":[201],"By":[202],"removing":[203],"need":[205],"for":[206],"auxiliary":[207],"reconstruction,":[211],"it":[212],"offers":[213],"practical,":[215],"efficient,":[216],"generalizable":[218],"way":[219],"detect":[221],"content.":[223]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}