{"id":"https://openalex.org/W3089485619","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206760","title":"Layer-wise Adversarial Training Approach to Improve Adversarial Robustness","display_name":"Layer-wise Adversarial Training Approach to Improve Adversarial Robustness","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3089485619","doi":"https://doi.org/10.1109/ijcnn48605.2020.9206760","mag":"3089485619"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9206760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100650023","display_name":"Xiaoyi Chen","orcid":"https://orcid.org/0000-0002-6224-791X"},"institutions":[{"id":"https://openalex.org/I4210149379","display_name":"NEC (China)","ror":"https://ror.org/04xrcx824","country_code":"CN","type":"company","lineage":["https://openalex.org/I118347220","https://openalex.org/I4210149379"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoyi CHEN","raw_affiliation_strings":["NEC Laboratories China, NEC (China) Co., Ltd., Beijing, China"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories China, NEC (China) Co., Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210149379"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100319347","display_name":"Ni Zhang","orcid":"https://orcid.org/0000-0002-6645-3366"},"institutions":[{"id":"https://openalex.org/I4210149379","display_name":"NEC (China)","ror":"https://ror.org/04xrcx824","country_code":"CN","type":"company","lineage":["https://openalex.org/I118347220","https://openalex.org/I4210149379"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ni ZHANG","raw_affiliation_strings":["NEC Laboratories China, NEC (China) Co., Ltd., Beijing, China"],"affiliations":[{"raw_affiliation_string":"NEC Laboratories China, NEC (China) Co., Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210149379"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100650023"],"corresponding_institution_ids":["https://openalex.org/I4210149379"],"apc_list":null,"apc_paid":null,"fwci":0.3977,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.69006419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"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/T14117","display_name":"Integrated Circuits and Semiconductor Failure Analysis","score":0.9787999987602234,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11515","display_name":"Bacillus and Francisella bacterial research","score":0.9434000253677368,"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":0.9580447673797607},{"id":"https://openalex.org/keywords/mnist-database","display_name":"MNIST database","score":0.8365691900253296},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7607858777046204},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.7276034355163574},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6972891092300415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6643416881561279},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5410403609275818},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5262814164161682},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5047045946121216},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4862038493156433},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.48542508482933044},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45356154441833496}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9580447673797607},{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.8365691900253296},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7607858777046204},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.7276034355163574},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6972891092300415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6643416881561279},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5410403609275818},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5262814164161682},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5047045946121216},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4862038493156433},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.48542508482933044},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45356154441833496},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9206760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9206760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1673923490","https://openalex.org/W1945616565","https://openalex.org/W2460937040","https://openalex.org/W2503523779","https://openalex.org/W2620038827","https://openalex.org/W2746600820","https://openalex.org/W2774644650","https://openalex.org/W2787708942","https://openalex.org/W2895033754","https://openalex.org/W2962710014","https://openalex.org/W2962761044","https://openalex.org/W2963070423","https://openalex.org/W2963143631","https://openalex.org/W2963207607","https://openalex.org/W2963389226","https://openalex.org/W2963744840","https://openalex.org/W2963857521","https://openalex.org/W2963879647","https://openalex.org/W2964153729","https://openalex.org/W2964253222","https://openalex.org/W2973831015","https://openalex.org/W3106412272","https://openalex.org/W4293846201","https://openalex.org/W4300511536","https://openalex.org/W4300725094","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6719080892","https://openalex.org/W6725195833","https://openalex.org/W6729756640","https://openalex.org/W6738471743","https://openalex.org/W6739868092","https://openalex.org/W6746608116","https://openalex.org/W6748475379","https://openalex.org/W6754762128","https://openalex.org/W6767618605"],"related_works":["https://openalex.org/W2950183588","https://openalex.org/W3080754722","https://openalex.org/W3093978547","https://openalex.org/W2953536436","https://openalex.org/W3203790781","https://openalex.org/W4313346231","https://openalex.org/W2738001131","https://openalex.org/W4285785480","https://openalex.org/W2997056298","https://openalex.org/W3000197790"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"have":[4],"delivered":[5],"state-of-the-art":[6],"performance":[7],"in":[8,14,63,92,99,127],"many":[9],"challenging":[10],"tasks,":[11],"such":[12,82,149],"as":[13,150],"computer":[15],"vision,":[16],"but":[17],"they":[18],"are":[19],"vulnerable":[20],"to":[21,40,70,78,112,115,134,206],"adversarial":[22,34,49,73,117,129,169,175,200],"attacks.":[23,50],"Adversarial":[24],"training":[25,31,170,176,196,201],"is":[26,76,138],"a":[27,59,65,100],"technique":[28],"for":[29],"augmenting":[30],"data":[32],"with":[33,198],"examples":[35],"and":[36,145,152,158,177,191],"has":[37],"empirically":[38,141],"proven":[39],"be":[41,113],"the":[42,53,103,116,128,136,166,194],"most":[43],"effective":[44],"method":[45,109,137],"of":[46,119,131],"defense":[47,181,209],"against":[48,182],"Motivated":[51],"by":[52,107,154],"fact":[54],"that":[55,83,165,178],"intermediate":[56],"layers":[57],"play":[58],"highly":[60],"important":[61],"role":[62],"maintaining":[64],"robust":[66,94],"model,":[67],"we":[68],"propose":[69],"extend":[71],"conventional":[72,174,199],"training,":[74],"which":[75,93,135],"designed":[77],"only":[79],"manipulate":[80],"input,":[81],"it":[84,179,204],"becomes":[85],"layer-wise":[86,101,168,195],"training.":[87],"Distinct":[88],"from":[89],"previous":[90],"studies":[91],"DNN":[95,132],"models":[96,133],"were":[97],"trained":[98],"manner,":[102],"layer":[104],"perturbation":[105],"introduced":[106],"our":[108],"theoretically":[110],"proves":[111],"equivalent":[114],"manipulation":[118],"network":[120],"inputs.":[121],"This":[122],"approach":[123,171],"guarantees":[124],"an":[125],"improvement":[126],"robustness":[130],"applied.":[139],"We":[140],"evaluated":[142],"both":[143],"shallow":[144],"deep":[146],"CNN":[147],"models,":[148],"VGG16":[151],"WideResNet28-10,":[153],"using":[155],"MNIST,":[156],"CIFAR-10,":[157],"CIFAR-100":[159],"datasets.":[160],"The":[161],"results":[162],"consistently":[163],"showed":[164],"proposed":[167],"significantly":[172],"outperforms":[173],"offers":[180],"all":[183],"mainstream":[184],"attacks":[185],"including":[186],"FGSM,":[187],"IFGSM,":[188],"PGD,":[189],"EoT,":[190],"C&W.":[192],"Combining":[193],"regime":[197],"would":[202],"make":[203],"possible":[205],"achieve":[207],"excellent":[208],"performance.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}