{"id":"https://openalex.org/W3133465759","doi":"https://doi.org/10.48550/arxiv.2005.09363","title":"Enhancing Certified Robustness via Smoothed Weighted Ensembling","display_name":"Enhancing Certified Robustness via Smoothed Weighted Ensembling","publication_year":2020,"publication_date":"2020-05-19","ids":{"openalex":"https://openalex.org/W3133465759","doi":"https://doi.org/10.48550/arxiv.2005.09363","mag":"3133465759"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2005.09363","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.09363","pdf_url":"https://arxiv.org/pdf/2005.09363","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.09363","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082461935","display_name":"Chizhou Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Chizhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064491965","display_name":"Yunzhen Feng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Yunzhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100621040","display_name":"Ranran Wang","orcid":"https://orcid.org/0000-0001-8032-7588","observed_orcids":["https://orcid.org/0000-0001-8032-7588"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Ranran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101641531","display_name":"Bin Dong","orcid":"https://orcid.org/0000-0003-1869-3784","observed_orcids":["https://orcid.org/0000-0003-1869-3784"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Bin","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":5,"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":0.9994999766349792,"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":0.9994999766349792,"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/T11424","display_name":"Security and Verification in Computing","score":9.999999747378752e-05,"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/T10142","display_name":"Formal Methods in Verification","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/randomized-smoothing","display_name":"randomized smoothing","score":0.7979999780654907},{"id":"https://openalex.org/keywords/certified-robustness","display_name":"certified robustness","score":0.9819999933242798},{"id":"https://openalex.org/keywords/adversarial-robustness","display_name":"adversarial robustness","score":0.7360000014305115},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"ensemble learning","score":0.656000018119812},{"id":"https://openalex.org/keywords/adaptive-forecasting","display_name":"adaptive prediction","score":0.6290000081062317},{"id":"https://openalex.org/keywords/upper-envelope","display_name":"upper envelope","score":0.35499998927116394},{"id":"https://openalex.org/keywords/training-efficiency","display_name":"training efficiency","score":0.32499998807907104}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6936233639717102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6639509201049805},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6513160467147827},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.6030306220054626},{"id":"https://openalex.org/C46304622","wikidata":"https://www.wikidata.org/wiki/Q374814","display_name":"Certification","level":2,"score":0.5303122997283936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4796034097671509},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47728386521339417},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4461020827293396},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36345118284225464},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2005.09363","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.09363","pdf_url":"https://arxiv.org/pdf/2005.09363","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,"listed_in":[],"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.2005.09363","doi":"https://doi.org/10.48550/arxiv.2005.09363","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.09363","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.09363","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.09363","pdf_url":"https://arxiv.org/pdf/2005.09363","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W9657784","https://openalex.org/W1686810756","https://openalex.org/W1966948031","https://openalex.org/W2108598243","https://openalex.org/W2123395972","https://openalex.org/W2128073546","https://openalex.org/W2135293965","https://openalex.org/W2147800946","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2486441166","https://openalex.org/W2552767274","https://openalex.org/W2579923771","https://openalex.org/W2594877703","https://openalex.org/W2610679774","https://openalex.org/W2721006554","https://openalex.org/W2754049786","https://openalex.org/W2755956102","https://openalex.org/W2777012514","https://openalex.org/W2786104118","https://openalex.org/W2786163515","https://openalex.org/W2787708942","https://openalex.org/W2789524546","https://openalex.org/W2794609696","https://openalex.org/W2799107510","https://openalex.org/W2803392236","https://openalex.org/W2803850896","https://openalex.org/W2807040120","https://openalex.org/W2883108656","https://openalex.org/W2890472662","https://openalex.org/W2890660842","https://openalex.org/W2891698621","https://openalex.org/W2892354372","https://openalex.org/W2896266676","https://openalex.org/W2898963688","https://openalex.org/W2899692219","https://openalex.org/W2911634294","https://openalex.org/W2912070915","https://openalex.org/W2913848079","https://openalex.org/W2922398468","https://openalex.org/W2948092553","https://openalex.org/W2951735139","https://openalex.org/W2962710014","https://openalex.org/W2962943487","https://openalex.org/W2963446712","https://openalex.org/W2963496101","https://openalex.org/W2963564844","https://openalex.org/W2964153729","https://openalex.org/W2964253222","https://openalex.org/W2970297683","https://openalex.org/W2981554050","https://openalex.org/W2996058201","https://openalex.org/W2996296329","https://openalex.org/W2996921661","https://openalex.org/W2997753396","https://openalex.org/W3005089002","https://openalex.org/W3005384972","https://openalex.org/W3007305010","https://openalex.org/W3008683143","https://openalex.org/W3009542902","https://openalex.org/W3013568554","https://openalex.org/W3034608990","https://openalex.org/W3093201595"],"related_works":["https://openalex.org/W4391528845","https://openalex.org/W2911634294","https://openalex.org/W3213780771","https://openalex.org/W3137096785","https://openalex.org/W3170033309","https://openalex.org/W4416251183","https://openalex.org/W4382449344","https://openalex.org/W3033193189","https://openalex.org/W3107520776","https://openalex.org/W4385804997"],"abstract_inverted_index":{"Randomized":[0],"smoothing":[1],"has":[2],"achieved":[3],"state-of-the-art":[4],"certified":[5,58],"robustness":[6],"against":[7],"$l_2$-norm":[8],"adversarial":[9],"attacks.":[10],"However,":[11],"it":[12],"is":[13],"not":[14],"wholly":[15],"resolved":[16],"on":[17],"how":[18],"to":[19,39,84,126],"find":[20],"the":[21,41,49,65,86,101],"optimal":[22,57,66],"base":[23],"classifier":[24],"for":[25],"randomized":[26,44],"smoothing.":[27],"In":[28],"this":[29],"work,":[30],"we":[31],"employ":[32],"a":[33,110,118,127,132],"Smoothed":[34],"WEighted":[35],"ENsembling":[36],"(SWEEN)":[37],"scheme":[38],"improve":[40],"performance":[42,125],"of":[43,91,104],"smoothed":[45],"classifiers.":[46],"We":[47,77],"show":[48,96],"ensembling":[50],"generality":[51],"that":[52,64,97],"SWEEN":[53,67,92,98,114],"can":[54,69,122],"help":[55],"achieve":[56,123],"robustness.":[59],"Furthermore,":[60],"theoretical":[61],"analysis":[62],"proves":[63],"model":[68,130],"be":[70],"obtained":[71],"from":[72],"training":[73,136],"under":[74],"mild":[75],"assumptions.":[76],"also":[78],"develop":[79],"an":[80],"adaptive":[81],"prediction":[82,87],"algorithm":[83],"reduce":[85],"and":[88],"certification":[89],"cost":[90],"models.":[93],"Extensive":[94],"experiments":[95],"models":[99,108,115,121],"outperform":[100],"upper":[102],"envelope":[103],"their":[105],"corresponding":[106],"candidate":[107],"by":[109],"large":[111,129],"margin.":[112],"Moreover,":[113],"constructed":[116],"using":[117],"few":[119],"small":[120],"comparable":[124],"single":[128],"with":[131],"notable":[133],"reduction":[134],"in":[135],"time.":[137]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2021-03-01T00:00:00"}