{"id":"https://openalex.org/W7128744166","doi":"https://doi.org/10.48448/h5v1-mz72","title":"Generating Risky Samples with Conformity Constraints via Diffusion Models","display_name":"Generating Risky Samples with Conformity Constraints via Diffusion Models","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7128744166","doi":"https://doi.org/10.48448/h5v1-mz72"},"language":"en","primary_location":{"id":"doi:10.48448/h5v1-mz72","doi":"https://doi.org/10.48448/h5v1-mz72","is_oa":true,"landing_page_url":"https://doi.org/10.48448/h5v1-mz72","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"},"volume":null,"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48448/h5v1-mz72","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125741655","display_name":"Association for Artificial Intelligence 2026","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Association for Artificial Intelligence 2026","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009228005","display_name":"Peng Cui","orcid":"https://orcid.org/0000-0003-2957-8511","observed_orcids":["https://orcid.org/0000-0003-2957-8511"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121130955","display_name":"Yue He","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121142997","display_name":"Kehan Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Kehan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121172487","display_name":"Zhengyi Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhengyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159893042","display_name":"Han Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu, Han","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001590631","display_name":"Xingxuan Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xingxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125701458","display_name":"Hao Zou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9580000042915344,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9580000042915344,"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":0.03669999912381172,"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/T10028","display_name":"Topic Modeling","score":0.0015999999595806003,"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/diffusion-models","display_name":"diffusion models","score":0.7609999775886536},{"id":"https://openalex.org/keywords/noisy-labels","display_name":"label noise","score":0.6850000023841858},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.6579999923706055},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.5550000071525574}],"concepts":[{"id":"https://openalex.org/C142172996","wikidata":"https://www.wikidata.org/wiki/Q221284","display_name":"Conformity","level":2,"score":0.8708000183105469},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7002999782562256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6244999766349792},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5622000098228455},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.5293999910354614},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4180999994277954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4041999876499176},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4009999930858612},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.39070001244544983},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.34299999475479126},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29350000619888306},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.28029999136924744},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25589999556541443},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C5911748","wikidata":"https://www.wikidata.org/wiki/Q4072285","display_name":"Conformity assessment","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48448/h5v1-mz72","doi":"https://doi.org/10.48448/h5v1-mz72","is_oa":true,"landing_page_url":"https://doi.org/10.48448/h5v1-mz72","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"}],"best_oa_location":{"id":"doi:10.48448/h5v1-mz72","doi":"https://doi.org/10.48448/h5v1-mz72","is_oa":true,"landing_page_url":"https://doi.org/10.48448/h5v1-mz72","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4392682261","https://openalex.org/W4415798333","https://openalex.org/W4391590689","https://openalex.org/W7212023476","https://openalex.org/W4415796450","https://openalex.org/W4414895149","https://openalex.org/W7160904403","https://openalex.org/W7163547594","https://openalex.org/W4413056593","https://openalex.org/W7127899083"],"abstract_inverted_index":{"Although":[0],"neural":[1],"networks":[2],"achieve":[3],"promising":[4],"performance":[5],"in":[6,46,86,105,170],"many":[7],"tasks,":[8],"they":[9],"may":[10],"still":[11],"fail":[12],"when":[13],"encountering":[14],"some":[15],"examples":[16],"and":[17,92,100,121,151,179],"bring":[18],"about":[19],"risks":[20],"to":[21,30,71,135,155],"applications.":[22,106],"To":[23,62,107],"discover":[24],"risky":[25,35,52,74,152],"samples,":[26],"previous":[27],"literature":[28],"attempts":[29],"search":[31],"for":[32],"patterns":[33],"of":[34,51,59,79,118,126,148,159,172,175,191,204],"samples":[36,53,75,91,203],"within":[37],"existing":[38,60,80,168],"datasets":[39],"or":[40],"inject":[41],"perturbation":[42],"into":[43],"them.":[44],"Yet":[45],"this":[47,64,109],"way":[48],"the":[49,57,77,87,116,139,146,157,173,188,192],"diversity":[50],"is":[54],"limited":[55],"by":[56,197],"coverage":[58,78],"datasets.":[61,81],"overcome":[63],"limitation,":[65],"recent":[66],"works":[67],"adopt":[68],"diffusion":[69],"models":[70,193],"produce":[72],"new":[73],"beyond":[76],"However,":[82],"these":[83],"methods":[84,169],"struggle":[85],"conformity":[88,133,180],"between":[89],"generated":[90,160,202],"expected":[93],"categories,":[94],"which":[95],"could":[96],"introduce":[97,145],"label":[98],"noise":[99],"severely":[101],"limit":[102],"their":[103],"effectiveness":[104],"address":[108],"issue,":[110],"we":[111],"propose":[112],"RiskyDiff":[113],"that":[114,165],"incorporates":[115],"embeddings":[117],"both":[119],"texts":[120],"images":[122],"as":[123,142,144],"implicit":[124],"constraints":[125],"category":[127,140],"conformity.":[128,206],"We":[129,184],"also":[130,185],"design":[131],"a":[132],"score":[134],"further":[136],"explicitly":[137],"strengthen":[138],"conformity,":[141],"well":[143],"mechanisms":[147],"embedding":[149],"screening":[150],"gradient":[153],"guidance":[154],"boost":[156],"risk":[158],"samples.":[161],"Extensive":[162],"experiments":[163],"reveal":[164],"RiskyDiff~greatly":[166],"outperforms":[167],"terms":[171],"degree":[174],"risk,":[176],"generation":[177],"quality,":[178],"with":[181,201],"conditioned":[182],"categories.":[183],"empirically":[186],"show":[187],"generalization":[189],"ability":[190],"can":[194],"be":[195],"enhanced":[196],"augmenting":[198],"training":[199],"data":[200],"high":[205]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-13T00:00:00"}