{"id":"https://openalex.org/W7131406304","doi":"https://doi.org/10.48550/arxiv.2602.19931","title":"Expanding the Role of Diffusion Models for Robust Classifier Training","display_name":"Expanding the Role of Diffusion Models for Robust Classifier Training","publication_year":2026,"publication_date":"2026-02-23","ids":{"openalex":"https://openalex.org/W7131406304","doi":"https://doi.org/10.48550/arxiv.2602.19931"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.19931","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.19931","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.2602.19931","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126698223","display_name":"Pin-Han Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Huang, Pin-Han","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126832693","display_name":"Shang-Tse Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Shang-Tse","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126846929","display_name":"Hsuan-Tien Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Hsuan-Tien","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5126698223"],"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":0.3767000138759613,"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":0.3767000138759613,"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":0.19920000433921814,"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":0.15649999678134918,"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/classifier","display_name":"Classifier (UML)","score":0.6459000110626221},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6442000269889832},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.6152999997138977},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5490999817848206},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5120000243186951},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43560001254081726},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.43290001153945923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6639999747276306},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6459000110626221},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6442000269889832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6367999911308289},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.6152999997138977},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5490999817848206},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5120000243186951},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48190000653266907},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43560001254081726},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.43290001153945923},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.2915000021457672},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.19931","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.19931","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.2602.19931","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.19931","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Incorporating":[0],"diffusion-generated":[1,109],"synthetic":[2,33,110,136],"data":[3,111,137],"into":[4,99],"adversarial":[5],"training":[6,15],"(AT)":[7],"has":[8],"been":[9],"shown":[10],"to":[11],"substantially":[12],"improve":[13],"the":[14,25,45,128],"of":[16,27,44,130],"robust":[17,52],"image":[18],"classifiers.":[19],"In":[20],"this":[21],"work,":[22],"we":[23,58],"extend":[24],"role":[26],"diffusion":[28,61,76,97,106,133],"models":[29,62,98],"beyond":[30],"merely":[31],"generating":[32],"data,":[34,46],"examining":[35],"whether":[36],"their":[37],"internal":[38],"representations,":[39],"which":[40],"encode":[41],"meaningful":[42],"features":[43],"can":[47],"provide":[48],"additional":[49],"benefits":[50],"for":[51],"classifier":[53],"training.":[54],"Through":[55],"systematic":[56],"experiments,":[57],"show":[59],"that":[60,65,73,95],"offer":[63],"representations":[64,77,107,134],"are":[66],"both":[67],"diverse":[68],"and":[69,72,108,122,135],"partially":[70],"robust,":[71],"explicitly":[74],"incorporating":[75,96],"as":[78],"an":[79],"auxiliary":[80],"learning":[81],"signal":[82],"during":[83],"AT":[84,100],"consistently":[85],"improves":[86],"robustness":[87],"across":[88],"settings.":[89],"Furthermore,":[90],"our":[91],"representation":[92],"analysis":[93],"indicates":[94],"encourages":[101],"more":[102],"disentangled":[103],"features,":[104],"while":[105],"play":[112],"complementary":[113],"roles":[114],"in":[115],"shaping":[116],"representations.":[117],"Experiments":[118],"on":[119],"CIFAR-10,":[120],"CIFAR-100,":[121],"ImageNet":[123],"validate":[124],"these":[125],"findings,":[126],"demonstrating":[127],"effectiveness":[129],"jointly":[131],"leveraging":[132],"within":[138],"AT.":[139]},"counts_by_year":[],"updated_date":"2026-02-26T06:34:08.959763","created_date":"2026-02-26T00:00:00"}