{"id":"https://openalex.org/W4416507446","doi":"https://doi.org/10.1109/iccv51701.2025.01063","title":"Riemannian-Geometric Fingerprints of Generative Models","display_name":"Riemannian-Geometric Fingerprints of Generative Models","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416507446","doi":"https://doi.org/10.1109/iccv51701.2025.01063"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.22802","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056817893","display_name":"Hae Jin Song","orcid":"https://orcid.org/0000-0002-0467-7399"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hae Jin Song","raw_affiliation_strings":["USC,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"USC,Department of Computer Science","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054494771","display_name":"Laurent Itti","orcid":"https://orcid.org/0000-0002-0168-2977"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laurent Itti","raw_affiliation_strings":["USC,Department of Computer Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"USC,Department of Computer Science","institution_ids":[]}]}],"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":"11425","last_page":"11435"},"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":0.3788999915122986,"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":0.3788999915122986,"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/T11448","display_name":"Face recognition and analysis","score":0.2784999907016754,"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/T12417","display_name":"Morphological variations and asymmetry","score":0.12409999966621399,"subfield":{"id":"https://openalex.org/subfields/2608","display_name":"Geometry and Topology"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5530999898910522},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5188999772071838},{"id":"https://openalex.org/keywords/geodesic","display_name":"Geodesic","score":0.5110999941825867},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.47369998693466187},{"id":"https://openalex.org/keywords/biometrics","display_name":"Biometrics","score":0.38119998574256897},{"id":"https://openalex.org/keywords/differential-geometry","display_name":"Differential geometry","score":0.3700000047683716},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.33250001072883606},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.3314000070095062},{"id":"https://openalex.org/keywords/law-enforcement","display_name":"Law enforcement","score":0.3203999996185303}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6481999754905701},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5530999898910522},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5188999772071838},{"id":"https://openalex.org/C165818556","wikidata":"https://www.wikidata.org/wiki/Q213488","display_name":"Geodesic","level":2,"score":0.5110999941825867},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.47369998693466187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46630001068115234},{"id":"https://openalex.org/C184297639","wikidata":"https://www.wikidata.org/wiki/Q177765","display_name":"Biometrics","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37059998512268066},{"id":"https://openalex.org/C192939610","wikidata":"https://www.wikidata.org/wiki/Q188444","display_name":"Differential geometry","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36160001158714294},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C2780262971","wikidata":"https://www.wikidata.org/wiki/Q44554","display_name":"Law enforcement","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C181104567","wikidata":"https://www.wikidata.org/wiki/Q761383","display_name":"Riemannian geometry","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.30880001187324524},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.3082999885082245},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30090001225471497},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C65059942","wikidata":"https://www.wikidata.org/wiki/Q270105","display_name":"Argumentation theory","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C9770341","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Geospatial analysis","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C67820243","wikidata":"https://www.wikidata.org/wiki/Q179164","display_name":"Unitary state","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C82668687","wikidata":"https://www.wikidata.org/wiki/Q3046456","display_name":"Earth mover's distance","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25270000100135803},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.22802","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.22802","pdf_url":"https://arxiv.org/pdf/2506.22802","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.22802","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.22802","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":"pmh:oai:arXiv.org:2506.22802","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.22802","pdf_url":"https://arxiv.org/pdf/2506.22802","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7671757787","display_name":"EFRI BRAID: Neuroscience Inspired Visual Analytics","funder_award_id":"2318101","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"breakthroughs":[1],"and":[2,18,38,51,116,133,140,177,182,188,241,267],"rapid":[3],"integration":[4],"of":[5,15,28,46,58,108,138,142,155,192,221],"generative":[6,99],"models":[7,31],"(GMs)":[8],"have":[9],"sparked":[10],"interest":[11],"in":[12,97,120,207,216,228],"the":[13,44,84,106,118,152,179,205,252],"problem":[14],"model":[16,59,239,255,265],"attribution":[17],"their":[19,30,34],"fingerprints.":[20],"For":[21],"instance,":[22],"service":[23],"providers":[24],"need":[25,85],"reliable":[26],"methods":[27],"authenticating":[29],"to":[32,42,86,150,168,198,262],"protect":[33],"IP,":[35],"while":[36],"users":[37],"law":[39],"enforcement":[40],"seek":[41],"verify":[43],"source":[45],"generated":[47],"content":[48],"for":[49,79,203],"accountability":[50],"trust.":[52],"In":[53],"addition,":[54],"a":[55,93,109,121,130,135,199,218,260],"growing":[56],"threat":[57],"collapse":[60],"is":[61,213],"arising,":[62],"as":[63,257,259],"more":[64,214],"model-generated":[65],"data":[66,176],"are":[67,76],"being":[68],"fed":[69],"back":[70],"into":[71],"sources":[72],"(e.g.,":[73],"YouTube)":[74],"that":[75,112,211],"often":[77],"harvested":[78],"training":[80],"(\"regurgitative":[81],"training\"),":[82],"heightening":[83],"differentiate":[87],"synthetic":[88],"from":[89,105,175],"human":[90],"data.":[91],"Yet,":[92],"gap":[94],"still":[95],"exists":[96],"understanding":[98],"models'":[100],"fingerprints,":[101],"we":[102,128],"believe,":[103],"stemming":[104],"lack":[107],"formal":[110],"framework":[111],"can":[113],"define,":[114],"represent,":[115],"analyze":[117],"fingerprints":[119,206],"principled":[122],"way.":[123],"To":[124],"address":[125],"this":[126],"gap,":[127],"take":[129],"geometric":[131],"approach":[132],"propose":[134],"new":[136,159,200],"definition":[137,160,249],"artifact":[139],"fingerprint":[141],"GMs":[143],"using":[144],"Riemannian":[145,173,190],"geometry,":[146],"which":[147],"allows":[148],"us":[149],"leverage":[151],"rich":[153],"theory":[154,197],"differential":[156],"geometry.":[157],"Our":[158],"generalizes":[161],"previous":[162],"work":[163],"(Song":[164],"et":[165],"al.,":[166],"2024)":[167],"non-Euclidean":[169],"manifolds":[170],"by":[171,233,236],"learning":[172],"metrics":[174],"replacing":[178],"Euclidean":[180],"distances":[181,187],"nearest-neighbor":[183],"search":[184],"with":[185],"geodesic":[186],"kNN-based":[189],"center":[191],"mass.":[193],"We":[194],"apply":[195],"our":[196,247],"gradient-based":[201],"algorithm":[202],"computing":[204],"practice.":[208],"Results":[209],"show":[210],"it":[212],"effective":[215],"distinguishing":[217],"large":[219],"array":[220],"GMs,":[222],"spanning":[223],"across":[224],"4":[225],"different":[226,230],"datasets":[227],"2":[229,242],"resolutions":[231],"(64":[232],"64,":[234],"256":[235],"256),":[237],"27":[238],"architectures,":[240],"modalities":[243],"(Vision,":[244],"Vision-Language).":[245],"Using":[246],"proposed":[248],"significantly":[250],"improves":[251],"performance":[253],"on":[254],"attribution,":[256],"well":[258],"generalization":[261],"unseen":[263],"datasets,":[264],"types,":[266],"modalities,":[268],"suggesting":[269],"its":[270],"practical":[271],"efficacy.":[272]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}