{"id":"https://openalex.org/W3199229028","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533815","title":"Bolstering Adversarial Robustness with Latent Disparity Regularization","display_name":"Bolstering Adversarial Robustness with Latent Disparity Regularization","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3199229028","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533815","mag":"3199229028"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5023565753","display_name":"David Schwartz","orcid":"https://orcid.org/0000-0001-7548-6373"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Schwartz","raw_affiliation_strings":["University of Arizona, Tucson, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Arizona, Tucson, United States of America","institution_ids":["https://openalex.org/I138006243"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079638101","display_name":"Gregory Ditzler","orcid":"https://orcid.org/0000-0001-6890-0935"},"institutions":[{"id":"https://openalex.org/I138006243","display_name":"University of Arizona","ror":"https://ror.org/03m2x1q45","country_code":"US","type":"education","lineage":["https://openalex.org/I138006243"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gregory Ditzler","raw_affiliation_strings":["University of Arizona, Tucson, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Arizona, Tucson, United States of America","institution_ids":["https://openalex.org/I138006243"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I138006243"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"8","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":1.0,"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":1.0,"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":0.9771000146865845,"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":0.9635999798774719,"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/mnist-database","display_name":"MNIST database","score":0.7775993347167969},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7441186904907227},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6474347710609436},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5947831869125366},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5894689559936523},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5493384003639221},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5316610336303711},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4745398759841919},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4700661599636078},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35745975375175476},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32222431898117065}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.7775993347167969},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7441186904907227},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6474347710609436},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5947831869125366},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5894689559936523},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5493384003639221},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5316610336303711},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4745398759841919},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4700661599636078},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35745975375175476},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32222431898117065},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533815","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W9657784","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1945616565","https://openalex.org/W2062164080","https://openalex.org/W2194775991","https://openalex.org/W2342045095","https://openalex.org/W2533641151","https://openalex.org/W2622826443","https://openalex.org/W2750384547","https://openalex.org/W2751924564","https://openalex.org/W2766447205","https://openalex.org/W2772825438","https://openalex.org/W2774018344","https://openalex.org/W2794002979","https://openalex.org/W2806021783","https://openalex.org/W2895948774","https://openalex.org/W2903382683","https://openalex.org/W2906186365","https://openalex.org/W2912447214","https://openalex.org/W2962914239","https://openalex.org/W2963207607","https://openalex.org/W2963389226","https://openalex.org/W2963626858","https://openalex.org/W2970115835","https://openalex.org/W2972672017","https://openalex.org/W3005576178","https://openalex.org/W3011206051","https://openalex.org/W3031351653","https://openalex.org/W3034672496","https://openalex.org/W3036048022","https://openalex.org/W3118608800","https://openalex.org/W4230026591","https://openalex.org/W4252979261","https://openalex.org/W4285706568","https://openalex.org/W4288359148","https://openalex.org/W4288618201","https://openalex.org/W4297738480","https://openalex.org/W6600428322","https://openalex.org/W6638667902","https://openalex.org/W6743812571","https://openalex.org/W6757107679","https://openalex.org/W6757253739","https://openalex.org/W6758648797","https://openalex.org/W6761839128","https://openalex.org/W6779483835"],"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/W4298079292"],"abstract_inverted_index":{"Recent":[0],"research":[1],"has":[2],"revealed":[3],"that":[4,17,190],"neural":[5,84,89],"networks":[6,90],"and":[7,47,79,119,130,172],"other":[8,214],"machine":[9,61],"learning":[10,62],"models":[11,63],"are":[12],"vulnerable":[13],"to":[14,19,32,52,145],"adversarial":[15,92,120,170,198,222],"attacks":[16,50,93],"aim":[18],"subvert":[20],"their":[21],"predictions'":[22],"integrity":[23,95],"or":[24],"privacy":[25],"by":[26,98,117,182],"adding":[27],"a":[28,55,65,101,162,226],"small":[29,227],"calculated":[30],"perturbation":[31],"inputs.":[33],"Further,":[34],"the":[35,40,43,108,111,128,146,150,155,158,191,209],"adversary":[36],"can":[37],"significantly":[38],"degrade":[39],"performance":[41],"of":[42,49,57,88,100,154,157],"model.":[44],"The":[45],"number":[46],"severity":[48],"continues":[51],"grow.":[53],"However,":[54],"dearth":[56],"techniques":[58],"robustly":[59],"defends":[60],"in":[64,114,149,197,232],"computationally":[66],"inexpensive":[67],"way.":[68],"Against":[69],"this":[70],"background,":[71],"we":[72],"propose":[73],"an":[74,175,202],"adversarially":[75],"robust":[76],"training":[77,174],"procedure":[78],"objective":[80],"function":[81],"for":[82],"arbitrary":[83],"network":[85],"architectures.":[86],"Robustness":[87],"against":[91,137],"on":[94,127,179],"is":[96,135,218],"achieved":[97],"augmentation":[99],"novel":[102],"regularization":[103,125,144],"term.":[104],"This":[105,216],"regularizer":[106,193],"penalizes":[107],"discrepancy":[109],"between":[110],"representations":[112],"induced":[113],"hidden":[115],"layers":[116],"benign":[118,233],"data.":[121],"We":[122],"benchmark":[123],"our":[124],"approach":[126],"Fashion-Mnist":[129],"Cifar-10":[131],"datasets.":[132],"Our":[133,187],"model":[134,178,205,211],"benchmarked":[136],"three":[138],"state-of-the-art":[139],"defense":[140],"methods,":[141],"namely:":[142],"(i)":[143],"largest":[147],"eigenvalue":[148],"Fisher":[151],"information":[152],"matrix":[153],"activity":[156],"terminal":[159],"layer,":[160],"(ii)":[161],"higher-level":[163],"representation":[164],"guided":[165],"denoising":[166],"autoencoder":[167],"(trained":[168],"with":[169,213,224],"examples),":[171],"(iii)":[173],"otherwise":[176],"undefended":[177,203],"data":[180],"distorted":[181],"additive":[183],"white":[184],"Gaussian":[185],"noise.":[186],"experiments":[188],"show":[189],"proposed":[192],"provides":[194],"significant":[195],"improvements":[196],"robustness":[199],"over":[200,220],"both":[201],"baseline":[204],"as":[206,208],"well":[207],"same":[210],"defended":[212],"techniques.":[215],"result":[217],"observed":[219],"several":[221],"budgets":[223],"only":[225],"(but":[228],"seemingly":[229],"unavoidable)":[230],"decline":[231],"test":[234],"accuracy.":[235]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}