{"id":"https://openalex.org/W4283758937","doi":"https://doi.org/10.1587/transinf.2021edp7239","title":"A Hybrid Bayesian-Convolutional Neural Network for Adversarial Robustness","display_name":"A Hybrid Bayesian-Convolutional Neural Network for Adversarial Robustness","publication_year":2022,"publication_date":"2022-06-30","ids":{"openalex":"https://openalex.org/W4283758937","doi":"https://doi.org/10.1587/transinf.2021edp7239"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2021edp7239","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2021edp7239","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/7/E105.D_2021EDP7239/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/7/E105.D_2021EDP7239/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046136958","display_name":"Thi Thu Thao Khong","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Thi Thu Thao KHONG","raw_affiliation_strings":["Nara Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090420165","display_name":"Takashi Nakada","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takashi NAKADA","raw_affiliation_strings":["International Professional University of Technology in Osaka"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Professional University of Technology in Osaka","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061486185","display_name":"Yasuhiko NAKASHIMA","orcid":null},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuhiko NAKASHIMA","raw_affiliation_strings":["Nara Institute of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2324,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58980774,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"E105.D","issue":"7","first_page":"1308","last_page":"1319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9998999834060669,"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":0.9998999834060669,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9815000295639038,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9677000045776367,"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/computer-science","display_name":"Computer science","score":0.8183923959732056},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7450394630432129},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6545230150222778},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6440795063972473},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.553066611289978},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5394983291625977},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5182335376739502},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4771963059902191},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4708249866962433},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.45034146308898926},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3707541227340698}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8183923959732056},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7450394630432129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6545230150222778},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6440795063972473},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.553066611289978},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5394983291625977},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5182335376739502},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4771963059902191},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4708249866962433},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.45034146308898926},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3707541227340698},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2021edp7239","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2021edp7239","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/7/E105.D_2021EDP7239/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2021edp7239","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2021edp7239","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E105.D/7/E105.D_2021EDP7239/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6731577112","display_name":"Revolution of Programmability in Non-von Neumann Platforms by Employing Tandem CGRA + Stochastic Computing","funder_award_id":"22H00515","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4283758937.pdf","grobid_xml":"https://content.openalex.org/works/W4283758937.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W71499226","https://openalex.org/W1665214252","https://openalex.org/W1673923490","https://openalex.org/W1826234144","https://openalex.org/W1945616565","https://openalex.org/W2108598243","https://openalex.org/W2180612164","https://openalex.org/W2194775991","https://openalex.org/W2243397390","https://openalex.org/W2460937040","https://openalex.org/W2549139847","https://openalex.org/W2620038827","https://openalex.org/W2640329709","https://openalex.org/W2787733970","https://openalex.org/W2884491628","https://openalex.org/W2890918255","https://openalex.org/W2891698621","https://openalex.org/W2895033754","https://openalex.org/W2946948417","https://openalex.org/W2962710014","https://openalex.org/W2963857521","https://openalex.org/W2965596382","https://openalex.org/W2996564870","https://openalex.org/W3035743198","https://openalex.org/W3135034047","https://openalex.org/W3151299405","https://openalex.org/W3208933490"],"related_works":["https://openalex.org/W2407375987","https://openalex.org/W2505726097","https://openalex.org/W2950975704","https://openalex.org/W2010643158","https://openalex.org/W3049691116","https://openalex.org/W2106867672","https://openalex.org/W4310268968","https://openalex.org/W3081214562","https://openalex.org/W2753713401","https://openalex.org/W2053745677"],"abstract_inverted_index":{"We":[0,71,78],"introduce":[1],"a":[2,31,66],"hybrid":[3],"Bayesian-convolutional":[4],"neural":[5],"network":[6],"(hyBCNN)":[7],"for":[8,87],"improving":[9],"the":[10,17,21,50,73,80,109,116,127],"robustness":[11],"against":[12],"adversarial":[13,95,100,119],"attacks":[14,120],"and":[15,35,46,60,102,124,145],"decreasing":[16],"computation":[18],"time":[19],"in":[20,115,140],"Bayesian":[22,57,61,83,92],"inference":[23,93],"phase.":[24],"Our":[25,97],"hyBCNN":[26,88,171],"models":[27],"are":[28,107],"built":[29],"from":[30],"part":[32],"of":[33,49,53,68,75,113,160],"BNN":[34],"CNN.":[36],"Based":[37],"on":[38,150,167],"pre-trained":[39,137],"CNNs,":[40],"we":[41],"only":[42],"replace":[43],"convolutional":[44,58],"layers":[45,64],"activation":[47,62,104],"function":[48],"initial":[51],"stage":[52],"CNNs":[54,76,114],"with":[55,130,147,164],"our":[56,169],"(BC)":[59],"(BA)":[63],"as":[65,122],"term":[67],"transfer":[69],"learning.":[70],"keep":[72],"remainder":[74],"unchanged.":[77],"adopt":[79],"Bayes":[81],"without":[82,177],"Learning":[84],"(BwoBL)":[85],"algorithm":[86],"networks":[89],"to":[90,118],"execute":[91],"towards":[94],"robustness.":[96],"proposal":[98],"outperforms":[99],"training":[101],"robust":[103],"function,":[105],"which":[106],"currently":[108],"outstanding":[110],"defense":[111],"methods":[112],"resistance":[117],"such":[121],"PGD":[123,158],"C&W.":[125],"Moreover,":[126],"proposed":[128],"architecture":[129],"BwoBL":[131],"can":[132],"easily":[133],"integrate":[134],"into":[135],"any":[136],"CNN,":[138],"especially":[139],"scaling":[141],"networks,":[142],"e.g.,":[143],"ResNet":[144],"EfficientNet,":[146],"better":[148],"performance":[149],"large-scale":[151],"datasets.":[152],"In":[153],"particular,":[154],"under":[155],"l\u221e":[156],"norm":[157],"attack":[159],"pixel":[161],"perturbation":[162],"\u03b5=4/255":[163],"100":[165],"iterations":[166],"ImageNet,":[168],"best":[170],"EfficientNet":[172],"reaches":[173],"93.92%":[174],"top-5":[175],"accuracy":[176],"additional":[178],"training.":[179]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}