{"id":"https://openalex.org/W4327969855","doi":"https://doi.org/10.3390/s23063252","title":"Between-Class Adversarial Training for Improving Adversarial Robustness of Image Classification","display_name":"Between-Class Adversarial Training for Improving Adversarial Robustness of Image Classification","publication_year":2023,"publication_date":"2023-03-20","ids":{"openalex":"https://openalex.org/W4327969855","doi":"https://doi.org/10.3390/s23063252","pmid":"https://pubmed.ncbi.nlm.nih.gov/36991962"},"language":"en","primary_location":{"id":"doi:10.3390/s23063252","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23063252","pdf_url":"https://www.mdpi.com/1424-8220/23/6/3252/pdf?version=1679277463","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/23/6/3252/pdf?version=1679277463","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029423578","display_name":"Desheng Wang","orcid":"https://orcid.org/0000-0001-5024-1628"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Desheng Wang","raw_affiliation_strings":["School of Electrical Engineering, Southwest Jiaotong University, Chengdu 611756, China"],"raw_orcid":"https://orcid.org/0000-0001-5024-1628","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Southwest Jiaotong University, Chengdu 611756, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101522875","display_name":"Weidong Jin","orcid":"https://orcid.org/0000-0001-9177-1609"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Jin","raw_affiliation_strings":["China-ASEAN International Joint Laboratory of Integrated Transportation, Nanning University, Nanning 541699, China","School of Electrical Engineering, Southwest Jiaotong University, Chengdu 611756, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China-ASEAN International Joint Laboratory of Integrated Transportation, Nanning University, Nanning 541699, China","institution_ids":[]},{"raw_affiliation_string":"School of Electrical Engineering, Southwest Jiaotong University, Chengdu 611756, China","institution_ids":["https://openalex.org/I4800084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079816703","display_name":"Yunpu Wu","orcid":"https://orcid.org/0000-0001-8135-9936"},"institutions":[{"id":"https://openalex.org/I102345215","display_name":"Xihua University","ror":"https://ror.org/04gwtvf26","country_code":"CN","type":"education","lineage":["https://openalex.org/I102345215"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunpu Wu","raw_affiliation_strings":["School of Electrical Engineering and Electronic Information, Xihua University, Chengdu 610039, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Electronic Information, Xihua University, Chengdu 610039, China","institution_ids":["https://openalex.org/I102345215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029423578"],"corresponding_institution_ids":["https://openalex.org/I4800084"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2673},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2673},"fwci":0.3955,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66993939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"23","issue":"6","first_page":"3252","last_page":"3252"},"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":0.9664000272750854,"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/T11515","display_name":"Bacillus and Francisella bacterial research","score":0.9004999995231628,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.8112483620643616},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7194858193397522},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7058680057525635},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.6687681078910828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5802851319313049},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5525293350219727},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5245749354362488},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43473124504089355},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.35849541425704956},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35192638635635376},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21690714359283447}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8112483620643616},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7194858193397522},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7058680057525635},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6687681078910828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5802851319313049},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5525293350219727},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5245749354362488},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43473124504089355},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.35849541425704956},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35192638635635376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21690714359283447},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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":5,"locations":[{"id":"doi:10.3390/s23063252","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23063252","pdf_url":"https://www.mdpi.com/1424-8220/23/6/3252/pdf?version=1679277463","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:36991962","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36991962","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:10057388","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10057388","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10057388/pdf/sensors-23-03252.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:86558422308a46baa95f5f3f2f56691e","is_oa":true,"landing_page_url":"https://doaj.org/article/86558422308a46baa95f5f3f2f56691e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 23, Iss 6, p 3252 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/23/6/3252/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s23063252","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors; Volume 23; Issue 6; Pages: 3252","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s23063252","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23063252","pdf_url":"https://www.mdpi.com/1424-8220/23/6/3252/pdf?version=1679277463","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4327969855.pdf"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1883420340","https://openalex.org/W1903029394","https://openalex.org/W1945616565","https://openalex.org/W2095705004","https://openalex.org/W2156876426","https://openalex.org/W2180612164","https://openalex.org/W2194775991","https://openalex.org/W2243397390","https://openalex.org/W2395611524","https://openalex.org/W2474352580","https://openalex.org/W2603766943","https://openalex.org/W2607219512","https://openalex.org/W2618043096","https://openalex.org/W2618530766","https://openalex.org/W2640329709","https://openalex.org/W2738001131","https://openalex.org/W2752159661","https://openalex.org/W2765233338","https://openalex.org/W2765424254","https://openalex.org/W2768188490","https://openalex.org/W2787496614","https://openalex.org/W2787708942","https://openalex.org/W2787733970","https://openalex.org/W2798302089","https://openalex.org/W2799032899","https://openalex.org/W2895033754","https://openalex.org/W2913266441","https://openalex.org/W2939411050","https://openalex.org/W2946498182","https://openalex.org/W2963031676","https://openalex.org/W2963037989","https://openalex.org/W2963612069","https://openalex.org/W2963857521","https://openalex.org/W2964201752","https://openalex.org/W2965154261","https://openalex.org/W2984306354","https://openalex.org/W2996564870","https://openalex.org/W3006834354","https://openalex.org/W3007702589","https://openalex.org/W3013038346","https://openalex.org/W3015957163","https://openalex.org/W3034842981","https://openalex.org/W3036982689","https://openalex.org/W3097573595","https://openalex.org/W3102720581","https://openalex.org/W3103557498","https://openalex.org/W3171998492","https://openalex.org/W3179916154","https://openalex.org/W4296940603","https://openalex.org/W6637162671","https://openalex.org/W6674330103","https://openalex.org/W6681151457","https://openalex.org/W6683161558","https://openalex.org/W6719080892","https://openalex.org/W6761100157","https://openalex.org/W6762624066","https://openalex.org/W6766725774","https://openalex.org/W6767248609","https://openalex.org/W6774681163","https://openalex.org/W6783646676"],"related_works":["https://openalex.org/W2950183588","https://openalex.org/W3080754722","https://openalex.org/W4383221314","https://openalex.org/W3093978547","https://openalex.org/W2953536436","https://openalex.org/W3203790781","https://openalex.org/W2997056298","https://openalex.org/W2738001131","https://openalex.org/W4285785480","https://openalex.org/W3127875750"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"have":[4],"been":[5],"known":[6,56],"to":[7,10,29,57,78,126,161],"be":[8,58,195],"vulnerable":[9],"adversarial":[11,30,114,124,133,159,237],"attacks.":[12,31],"Adversarial":[13,99],"training":[14],"(AT)":[15],"is,":[16],"so":[17],"far,":[18],"the":[19,25,33,45,62,67,80,84,121,155,167,171,189,199,235],"only":[20],"method":[21],"that":[22,102,225],"can":[23,194],"guarantee":[24],"robustness":[26,34,68,81,168,231],"of":[27,38,49,71,89,131,158,175,191,212],"DNNs":[28],"However,":[32],"generalization":[35,47,64,69,82,86,169,173,232],"accuracy":[36,48,65,70],"gain":[37],"AT":[39],"is":[40,55],"still":[41],"far":[42],"lower":[43],"than":[44,234],"standard":[46,63,85,108,172,186],"an":[50,72],"undefended":[51],"model,":[52],"and":[53,66,83,119,149,170,206,218],"there":[54],"a":[59,93,128,143,210],"trade-off":[60,88],"between":[61],"adversarially":[73],"trained":[74],"model.":[75],"In":[76],"order":[77],"improve":[79],"performance":[87,174,233],"AT,":[90],"we":[91],"propose":[92,139],"novel":[94],"defense":[95,238],"algorithm":[96],"called":[97],"Between-Class":[98,104],"Training":[100],"(BCAT)":[101],"combines":[103],"learning":[105],"(BC-learning)":[106],"with":[107],"AT.":[109,136,176],"Specifically,":[110],"BCAT":[111,148],"mixes":[112],"two":[113],"examples":[115,125,134,160],"from":[116],"different":[117],"classes":[118],"uses":[120],"mixed":[122],"between-class":[123,163],"train":[127],"model":[129],"instead":[130],"original":[132],"during":[135],"We":[137,197],"further":[138],"BCAT+":[140,150],"which":[141],"adopts":[142],"more":[144],"powerful":[145],"mixing":[146],"method.":[147],"impose":[151],"effective":[152],"regularization":[153],"on":[154,215],"feature":[156],"distribution":[157],"enlarge":[162],"distance,":[164],"thus":[165],"improving":[166],"The":[177,221],"proposed":[178,200],"algorithms":[179,201,227],"do":[180],"not":[181],"introduce":[182],"any":[183],"hyperparameters":[184,192],"into":[185],"AT;":[187],"therefore,":[188],"process":[190],"searching":[193],"avoided.":[196],"evaluate":[198],"under":[202],"both":[203],"white-box":[204],"attacks":[205,208],"black-box":[207],"using":[209],"spectrum":[211],"perturbation":[213],"values":[214],"CIFAR-10,":[216],"CIFAR-100,":[217],"SVHN":[219],"datasets.":[220],"research":[222],"findings":[223],"indicate":[224],"our":[226],"achieve":[228],"better":[229],"global":[230],"state-of-the-art":[236],"methods.":[239]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
