{"id":"https://openalex.org/W4312465788","doi":"https://doi.org/10.1109/icpr56361.2022.9956053","title":"Introducing Diversity In Feature Scatter Adversarial Training Via Synthesis","display_name":"Introducing Diversity In Feature Scatter Adversarial Training Via Synthesis","publication_year":2022,"publication_date":"2022-08-21","ids":{"openalex":"https://openalex.org/W4312465788","doi":"https://doi.org/10.1109/icpr56361.2022.9956053"},"language":"en","primary_location":{"id":"doi:10.1109/icpr56361.2022.9956053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956053","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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/A5020393669","display_name":"Satyadwyoom Kumar","orcid":"https://orcid.org/0000-0002-3929-5024"},"institutions":[{"id":"https://openalex.org/I36090812","display_name":"Netaji Subhas University of Technology","ror":"https://ror.org/01fczmh85","country_code":"IN","type":"education","lineage":["https://openalex.org/I36090812"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Satyadwyoom Kumar","raw_affiliation_strings":["Netaji Subhas Institute of Technology,Dept. Electronics and Communication,New-Delhi,India","Dept. Electronics and Communication, Netaji Subhas Institute of Technology, New-Delhi, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Netaji Subhas Institute of Technology,Dept. Electronics and Communication,New-Delhi,India","institution_ids":["https://openalex.org/I36090812"]},{"raw_affiliation_string":"Dept. Electronics and Communication, Netaji Subhas Institute of Technology, New-Delhi, India","institution_ids":["https://openalex.org/I36090812"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000267964","display_name":"Apurva Narayan","orcid":"https://orcid.org/0000-0001-7203-8698"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]},{"id":"https://openalex.org/I2800978909","display_name":"Kelowna General Hospital","ror":"https://ror.org/01j25h453","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I104778310","https://openalex.org/I2800978909"]},{"id":"https://openalex.org/I822440","display_name":"Okanagan University College","ror":"https://ror.org/02mxmh518","country_code":"CA","type":"education","lineage":["https://openalex.org/I822440"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Apurva Narayan","raw_affiliation_strings":["The University of British Columbia,Dept. Computer Science,Kelowna,Canada","Dept. Computer Science, The University of British Columbia, Kelowna, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of British Columbia,Dept. Computer Science,Kelowna,Canada","institution_ids":["https://openalex.org/I2800978909","https://openalex.org/I822440"]},{"raw_affiliation_string":"Dept. Computer Science, The University of British Columbia, Kelowna, Canada","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5020393669"],"corresponding_institution_ids":["https://openalex.org/I36090812"],"apc_list":null,"apc_paid":null,"fwci":0.1043,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.32697403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"26","issue":null,"first_page":"3069","last_page":"3075"},"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":0.973800003528595,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.9180468916893005},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.75228351354599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.634353518486023},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5841344594955444},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5655070543289185},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5310018062591553},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4882993698120117},{"id":"https://openalex.org/keywords/white-box","display_name":"White box","score":0.450398325920105},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4428193271160126},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.43923237919807434},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1128174364566803}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9180468916893005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.75228351354599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.634353518486023},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5841344594955444},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5655070543289185},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5310018062591553},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4882993698120117},{"id":"https://openalex.org/C180932941","wikidata":"https://www.wikidata.org/wiki/Q997233","display_name":"White box","level":2,"score":0.450398325920105},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4428193271160126},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.43923237919807434},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1128174364566803},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr56361.2022.9956053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr56361.2022.9956053","pdf_url":null,"source":{"id":"https://openalex.org/S4363607731","display_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 26th International Conference on Pattern Recognition (ICPR)","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":53,"referenced_works":["https://openalex.org/W1673923490","https://openalex.org/W1901129140","https://openalex.org/W1945616565","https://openalex.org/W2158131535","https://openalex.org/W2335728318","https://openalex.org/W2739748921","https://openalex.org/W2786104118","https://openalex.org/W2786118190","https://openalex.org/W2892128688","https://openalex.org/W2898681588","https://openalex.org/W2942630857","https://openalex.org/W2949384876","https://openalex.org/W2962759300","https://openalex.org/W2963143631","https://openalex.org/W2963306805","https://openalex.org/W2963448658","https://openalex.org/W2963560523","https://openalex.org/W2963857521","https://openalex.org/W2964197269","https://openalex.org/W2964201752","https://openalex.org/W2986674980","https://openalex.org/W2996564870","https://openalex.org/W2997502936","https://openalex.org/W3034734289","https://openalex.org/W3035032188","https://openalex.org/W3043786973","https://openalex.org/W3118608800","https://openalex.org/W4288359148","https://openalex.org/W4288363925","https://openalex.org/W4293846201","https://openalex.org/W4320013936","https://openalex.org/W6637162671","https://openalex.org/W6639824700","https://openalex.org/W6640425456","https://openalex.org/W6682962330","https://openalex.org/W6703116779","https://openalex.org/W6739868092","https://openalex.org/W6741832134","https://openalex.org/W6744679260","https://openalex.org/W6747536865","https://openalex.org/W6747920752","https://openalex.org/W6748204703","https://openalex.org/W6748475379","https://openalex.org/W6754623918","https://openalex.org/W6755574775","https://openalex.org/W6757367567","https://openalex.org/W6761100157","https://openalex.org/W6766725774","https://openalex.org/W6771809012","https://openalex.org/W6774357917","https://openalex.org/W6774681163","https://openalex.org/W6780973103","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W2886520477","https://openalex.org/W4297846880","https://openalex.org/W2950942529","https://openalex.org/W4324108765","https://openalex.org/W4307929675","https://openalex.org/W4285052570"],"abstract_inverted_index":{"In":[0],"an":[1,90],"attempt":[2],"to":[3,31,42,53,64,105],"understand":[4],"how":[5],"deep":[6],"learning":[7],"models":[8],"interpret":[9],"inputs,":[10],"it":[11],"has":[12,61],"been":[13],"found":[14],"that":[15,81,92],"they":[16],"change":[17],"their":[18],"prediction":[19],"when":[20],"a":[21,67,121],"carefully":[22],"optimized":[23],"imperceptible":[24],"noise":[25],"termed":[26],"adversarial":[27,54,59,75,97,102,109],"perturbation":[28],"is":[29],"added":[30],"the":[32,73,95,100,108,136],"input":[33],"data.":[34,56],"Many":[35],"researchers":[36],"are":[37],"focusing":[38],"on":[39],"developing":[40],"methods":[41,48,138],"counter":[43],"such":[44,47,66,126],"effects,":[45],"but":[46,69],"do":[49],"not":[50],"generalize":[51],"well":[52],"test":[55],"Recently,":[57],"Feature-Scatter":[58,96],"training":[60,76,98,103],"come":[62],"up":[63],"solve":[65],"problem,":[68],"this":[70,86],"method":[71],"uses":[72],"traditional":[74],"framework":[77,104,133],"as":[78,127],"its":[79],"basis":[80],"cannot":[82],"generate":[83],"diverse":[84],"perturbations.In":[85],"paper,":[87],"we":[88],"propose":[89],"approach":[91],"combines":[93],"both":[94,140],"and":[99,130,144],"generator-based":[101],"optimally":[106],"explore":[107],"data":[110],"manifold":[111],"achieving":[112],"better":[113],"robust":[114],"generalization.":[115],"We":[116],"perform":[117],"extensive":[118],"experimentation":[119],"across":[120],"wide":[122],"variety":[123],"of":[124],"datasets":[125],"Cifar10,":[128],"Cifar100,":[129],"SVHN.":[131],"Our":[132],"significantly":[134],"outperforms":[135],"state-of-the-art":[137],"against":[139],"strong":[141],"white-box":[142],"attacks":[143],"black-box":[145],"attacks.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2025-10-10T00:00:00"}