{"id":"https://openalex.org/W7160301108","doi":"https://doi.org/10.48550/arxiv.2605.01718","title":"Dual-branch Robust Unlearnable Examples","display_name":"Dual-branch Robust Unlearnable Examples","publication_year":2026,"publication_date":"2026-05-03","ids":{"openalex":"https://openalex.org/W7160301108","doi":"https://doi.org/10.48550/arxiv.2605.01718"},"language":"en","primary_location":{"id":"pmh:oai:pure.atira.dk:publications/c18cbb82-f6ca-42ce-8996-90ed965921f7","is_oa":false,"landing_page_url":"https://scholars.cityu.edu.hk/en/publications/c18cbb82-f6ca-42ce-8996-90ed965921f7","pdf_url":null,"source":{"id":"https://openalex.org/S7407055387","display_name":"CityU Scholars","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"WANG, X, Zhang, H, PAN, W, Zhou, Z, Jiang, C, Zeng, L & JIA, X 2026, Dual-branch Robust Unlearnable Examples. in Proceedings of the 43rd International Conference on Machine Learning (ICML 2026).","raw_type":"info:eu-repo/semantics/conferenceObject"},"type":"conference-paper","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.01718","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135283723","display_name":"Xianlong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xianlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036365195","display_name":"Hangtao Zhang","orcid":"https://orcid.org/0000-0002-6805-6401"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hangtao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101920502","display_name":"Wenbo Pan","orcid":"https://orcid.org/0000-0002-5527-2914"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Wenbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135387863","display_name":"Ziqi Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Ziqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008065088","display_name":"Changsong Jiang","orcid":"https://orcid.org/0000-0002-6510-3380"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Changsong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135369634","display_name":"Li Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135303572","display_name":"Xiaohua Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Xiaohua","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45821364,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.6991000175476074,"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":0.6991000175476074,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0940999984741211,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.049300000071525574,"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/robustness","display_name":"Robustness (evolution)","score":0.8206999897956848},{"id":"https://openalex.org/keywords/perturbation","display_name":"Perturbation (astronomy)","score":0.459199994802475},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3982999920845032},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.3163999915122986},{"id":"https://openalex.org/keywords/design-of-experiments","display_name":"Design of experiments","score":0.28290000557899475}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8206999897956848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6546000242233276},{"id":"https://openalex.org/C177918212","wikidata":"https://www.wikidata.org/wiki/Q803623","display_name":"Perturbation (astronomy)","level":2,"score":0.459199994802475},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3982999920845032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38370001316070557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3366999924182892},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.33320000767707825},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33000001311302185},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C34559072","wikidata":"https://www.wikidata.org/wiki/Q2334061","display_name":"Design of experiments","level":2,"score":0.28290000557899475},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:pure.atira.dk:publications/c18cbb82-f6ca-42ce-8996-90ed965921f7","is_oa":false,"landing_page_url":"https://scholars.cityu.edu.hk/en/publications/c18cbb82-f6ca-42ce-8996-90ed965921f7","pdf_url":null,"source":{"id":"https://openalex.org/S7407055387","display_name":"CityU Scholars","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"WANG, X, Zhang, H, PAN, W, Zhou, Z, Jiang, C, Zeng, L & JIA, X 2026, Dual-branch Robust Unlearnable Examples. in Proceedings of the 43rd International Conference on Machine Learning (ICML 2026).","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2605.01718","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01718","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":"doi:10.48550/arxiv.2605.01718","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01718","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":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Unlearnable":[0],"examples":[1],"(UEs)":[2],"aim":[3],"to":[4,12,26,59,74,85,144],"compromise":[5],"model":[6],"training":[7],"by":[8],"injecting":[9],"imperceptible":[10],"perturbations":[11,52,64],"clean":[13],"samples.":[14],"However,":[15],"existing":[16],"UE":[17,130],"schemes":[18,131],"exhibit":[19],"limited":[20],"robustness":[21,80,126],"against":[22],"advanced":[23],"defenses":[24],"due":[25],"their":[27],"heuristic":[28],"design":[29,69],"or":[30],"narrowly":[31],"scoped":[32],"domain":[33,73],"perturbations.":[34],"To":[35,95],"address":[36],"this,":[37],"we":[38,99],"propose":[39,101],"\\texttt{DUNE},":[40],"a":[41,137],"\\underline{\\textbf{D}}ual-branch":[42],"\\underline{\\textbf{UN}}learnable":[43],"\\underline{\\textbf{E}}nsemble":[44],"perturbation":[45,72],"optimization":[46],"approach.":[47],"Specifically,":[48],"\\texttt{DUNE}":[49],"separately":[50],"optimizes":[51],"in":[53],"the":[54,61,71,83,112],"spatial":[55],"and":[56,65,81,121],"color":[57],"domains":[58],"establish":[60],"mapping":[62],"between":[63],"shift-induced":[66],"labels.":[67],"This":[68],"extends":[70],"increase":[75],"noise":[76],"intensity":[77],"for":[78],"improving":[79],"drives":[82],"models":[84,110],"learn":[86],"perturbation-oriented":[87],"features":[88],"with":[89],"degraded":[90],"generalization,":[91],"thereby":[92],"achieving":[93],"unlearnability.":[94],"strengthen":[96],"\\texttt{DUNE}'s":[97,125],"performance,":[98],"further":[100],"an":[102],"unlearnability-enhancing":[103],"ensemble":[104],"strategy":[105],"that":[106,124],"aggregates":[107],"diverse":[108],"pre-trained":[109],"during":[111],"dual-branch":[113],"optimization.":[114],"Extensive":[115],"experiments":[116],"on":[117],"benchmark":[118],"datasets":[119],"CIFAR-10":[120],"ImageNet":[122],"verify":[123],"outperforms":[127],"12":[128],"SOTA":[129],"under":[132],"7":[133],"mainstream":[134],"defenses,":[135],"yielding":[136],"lower":[138],"average":[139],"test":[140],"accuracy":[141],"of":[142],"14.95%":[143],"50.82%.":[145]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}