{"id":"https://openalex.org/W7167084326","doi":"https://doi.org/10.48550/arxiv.2607.00183","title":"DriftScope: Measuring The Hidden Effects of Diffusion Model Adaptation","display_name":"DriftScope: Measuring The Hidden Effects of Diffusion Model Adaptation","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W7167084326","doi":"https://doi.org/10.48550/arxiv.2607.00183"},"language":null,"primary_location":{"id":"pmh:oai:zenodo.org:21511341","is_oa":true,"landing_page_url":"https://arxiv.org/abs/arXiv:2607.00183","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"European Conference on Computer Vision (ECCV)","raw_type":"info:eu-repo/semantics/conferencePaper"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/arXiv:2607.00183","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062781240","display_name":"H\u00e9ctor Laria","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laria, H\u00e9ctor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108783818","display_name":"Yiping Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Yiping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122132793","display_name":"Julian D. Santamaria","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Santamaria, Julian D.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139913854","display_name":"Kai Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139856124","display_name":"Bogdan Raducanu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raducanu, Bogdan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139874177","display_name":"Joost van de Weijer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"van de Weijer, Joost","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5119833538","display_name":"Alexandra Gomez-Villa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gomez-Villa, Alexandra","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.28279998898506165,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.28279998898506165,"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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.24150000512599945,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.08259999752044678,"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/aggregate","display_name":"Aggregate (composite)","score":0.5218999981880188},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.43860000371932983},{"id":"https://openalex.org/keywords/skew","display_name":"Skew","score":0.34860000014305115},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.3467999994754791},{"id":"https://openalex.org/keywords/artifact","display_name":"Artifact (error)","score":0.3465999960899353},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.3398999869823456},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.3280999958515167}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6741999983787537},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5218999981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.510200023651123},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.43860000371932983},{"id":"https://openalex.org/C43711488","wikidata":"https://www.wikidata.org/wiki/Q7534783","display_name":"Skew","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3467999994754791},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.3465999960899353},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3246000111103058},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32199999690055847},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C169087156","wikidata":"https://www.wikidata.org/wiki/Q2131593","display_name":"Framing (construction)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C60777511","wikidata":"https://www.wikidata.org/wiki/Q3045002","display_name":"Concept drift","level":3,"score":0.2718000113964081},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:21511341","is_oa":true,"landing_page_url":"https://arxiv.org/abs/arXiv:2607.00183","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"European Conference on Computer Vision (ECCV)","raw_type":"info:eu-repo/semantics/conferencePaper"},{"id":"doi:10.48550/arxiv.2607.00183","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.00183","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,"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:zenodo.org:21511341","is_oa":true,"landing_page_url":"https://arxiv.org/abs/arXiv:2607.00183","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"European Conference on Computer Vision (ECCV)","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Adapting":[0],"pre-trained":[1],"text-to-image":[2],"diffusion":[3],"models,":[4],"whether":[5],"to":[6,62,91,171,181],"learn":[7],"new":[8],"visual":[9,159],"concepts":[10,44,160],"or":[11,184],"erase":[12],"unwanted":[13],"ones,":[14],"is":[15,27,55,66,116,189],"routinely":[16],"evaluated":[17],"on":[18],"its":[19],"intended":[20],"effects":[21],"alone.":[22],"We":[23],"argue":[24],"this":[25,133],"framing":[26],"incomplete.":[28],"Through":[29],"sparse":[30],"autoencoder":[31],"analysis":[32],"and":[33,60,76,94,111,151],"zero-shot":[34,86],"classification,":[35],"we":[36,138],"demonstrate":[37],"that":[38,47,145,194],"adaptation":[39,107],"systematically":[40],"damages":[41],"semantically":[42],"unrelated":[43],"in":[45],"ways":[46],"aggregate":[48,195],"metrics":[49],"structurally":[50],"cannot":[51,197],"surface:":[52],"when":[53,70],"damage":[54],"severe":[56],"enough":[57],"for":[58],"FID":[59,75],"KID":[61,77],"respond,":[63],"the":[64,71,106,175],"model":[65,72,149,185],"already":[67],"nearly":[68],"unusable;":[69],"remains":[73],"functional,":[74],"stay":[78],"flat":[79],"while":[80],"specific":[81],"classes":[82],"silently":[83],"suffer":[84],"worst-case":[85],"accuracy":[87],"drops":[88],"of":[89,105,120,127,156],"up":[90],"18.9":[92],"points":[93],"concept-level":[95,192],"distributions":[96],"shift":[97],"dramatically.":[98],"This":[99],"pattern":[100],"appears":[101],"at":[102,174],"both":[103],"ends":[104],"spectrum":[108],"(concept":[109],"customization":[110],"concept":[112],"unlearning),":[113],"suggesting":[114],"it":[115],"a":[117,141,153,168],"systematic":[118],"consequence":[119],"weight-level":[121],"modification":[122],"rather":[123],"than":[124],"an":[125,190],"artifact":[126],"any":[128,147],"particular":[129],"method.":[130],"To":[131],"surface":[132],"hidden":[134],"drift":[135,173],"before":[136],"deployment,":[137],"introduce":[139],"DriftScope,":[140],"prompt-level":[142],"diagnostic":[143],"tool":[144],"takes":[146],"two":[148],"checkpoints":[150],"returns":[152],"ranked":[154],"list":[155],"tokens":[157],"whose":[158],"have":[161],"shifted":[162],"most":[163],"between":[164],"them.":[165],"DriftScope":[166],"optimizes":[167],"soft":[169],"prompt":[170],"attribute":[172],"token":[176],"level":[177],"without":[178],"requiring":[179],"access":[180],"real":[182],"data":[183],"internals.":[186],"The":[187],"result":[188],"interpretable,":[191],"audit":[193],"evaluation":[196],"provide.":[198]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-03T00:00:00"}