{"id":"https://openalex.org/W4388312064","doi":"https://doi.org/10.1016/j.neucom.2023.127000","title":"Improving robustness for vision transformer with a simple dynamic scanning augmentation","display_name":"Improving robustness for vision transformer with a simple dynamic scanning augmentation","publication_year":2023,"publication_date":"2023-11-03","ids":{"openalex":"https://openalex.org/W4388312064","doi":"https://doi.org/10.1016/j.neucom.2023.127000"},"language":"en","primary_location":{"id":"doi:10.1016/j.neucom.2023.127000","doi":"https://doi.org/10.1016/j.neucom.2023.127000","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2023.127000","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-c","cwts-core","dongbi-b","doyens","jufo-2","ki-jl-2","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.neucom.2023.127000","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001629940","display_name":"Shashank Kotyan","orcid":"https://orcid.org/0000-0003-1235-3316","observed_orcids":["https://orcid.org/0000-0003-1235-3316"]},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shashank Kotyan","raw_affiliation_strings":["Department of Information Science and Technology, Kyushu University, Fukuoka, 819-0395, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1235-3316","affiliations":[{"raw_affiliation_string":"Department of Information Science and Technology, Kyushu University, Fukuoka, 819-0395, Japan","institution_ids":["https://openalex.org/I135598925"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028815763","display_name":"Danilo Vasconcellos Vargas","orcid":"https://orcid.org/0000-0001-7442-1279","observed_orcids":["https://orcid.org/0000-0001-7442-1279"]},"institutions":[{"id":"https://openalex.org/I135598925","display_name":"Kyushu University","ror":"https://ror.org/00p4k0j84","country_code":"JP","type":"education","lineage":["https://openalex.org/I135598925"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Danilo Vasconcellos Vargas","raw_affiliation_strings":["Department of Information Science and Technology, Kyushu University, Fukuoka, 819-0395, Japan"],"raw_orcid":"https://orcid.org/0000-0001-7442-1279","affiliations":[{"raw_affiliation_string":"Department of Information Science and Technology, Kyushu University, Fukuoka, 819-0395, Japan","institution_ids":["https://openalex.org/I135598925"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5028815763"],"corresponding_institution_ids":["https://openalex.org/I135598925"],"apc_list":{"value":2470,"currency":"USD","value_usd":2470},"apc_paid":{"value":2470,"currency":"USD","value_usd":2470},"fwci":0.6311,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.66229018,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"565","issue":null,"first_page":"127000","last_page":"127000"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9922000169754028,"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":0.9922000169754028,"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":0.00559999980032444,"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"}},{"id":"https://openalex.org/T12357","display_name":"Digital Media Forensic Detection","score":0.00019999999494757503,"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/vision-transformer","display_name":"vision transformer","score":0.8799999952316284},{"id":"https://openalex.org/keywords/adversarial-robustness","display_name":"adversarial robustness","score":0.878000020980835},{"id":"https://openalex.org/keywords/data-augmentation","display_name":"data augmentation","score":0.6679999828338623},{"id":"https://openalex.org/keywords/adaptive-attention-mechanism","display_name":"adaptive attention","score":0.6060000061988831},{"id":"https://openalex.org/keywords/adversarial-attacks","display_name":"adversarial attacks","score":0.6039999723434448},{"id":"https://openalex.org/keywords/image-classification-accuracy","display_name":"image classification accuracy","score":0.621999979019165}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8150281310081482},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7537072896957397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5575051307678223},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5466431379318237},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5153245329856873},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.49011048674583435},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4433349370956421},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4323119521141052},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4028290808200836},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3559862971305847},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13730254769325256},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0888873040676117},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/j.neucom.2023.127000","doi":"https://doi.org/10.1016/j.neucom.2023.127000","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2023.127000","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-c","cwts-core","dongbi-b","doyens","jufo-2","ki-jl-2","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2311.00441","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.00441","pdf_url":"https://arxiv.org/pdf/2311.00441","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2311.00441","doi":"https://doi.org/10.48550/arxiv.2311.00441","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.00441","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1016/j.neucom.2023.127000","doi":"https://doi.org/10.1016/j.neucom.2023.127000","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neucom.2023.127000","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-c","cwts-core","dongbi-b","doyens","jufo-2","ki-jl-2","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5955335536","display_name":"Learning based on Self-Organization: Pioneering a New Foundation for AI","funder_award_id":"22K19814","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"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388312064.pdf","grobid_xml":"https://content.openalex.org/works/W4388312064.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1973190657","https://openalex.org/W2117539524","https://openalex.org/W2165715764","https://openalex.org/W2285469787","https://openalex.org/W2626778328","https://openalex.org/W2765424254","https://openalex.org/W2810408730","https://openalex.org/W2949718784","https://openalex.org/W2949736877","https://openalex.org/W2963321141","https://openalex.org/W2963351113","https://openalex.org/W2979826702","https://openalex.org/W3015625436","https://openalex.org/W3030520226","https://openalex.org/W3033210410","https://openalex.org/W3034445277","https://openalex.org/W3035022492","https://openalex.org/W3095422700","https://openalex.org/W3107331169","https://openalex.org/W3121523901","https://openalex.org/W3131500599","https://openalex.org/W3133696297","https://openalex.org/W3138516171","https://openalex.org/W3143373604","https://openalex.org/W3165924482","https://openalex.org/W3168649818","https://openalex.org/W3170841864","https://openalex.org/W3171125843","https://openalex.org/W3171516518","https://openalex.org/W3197200122","https://openalex.org/W4205185581","https://openalex.org/W4224086587","https://openalex.org/W4295224299","https://openalex.org/W4295241292","https://openalex.org/W4315606099","https://openalex.org/W4319872806","https://openalex.org/W4353004773","https://openalex.org/W4411245291"],"related_works":["https://openalex.org/W4312957757","https://openalex.org/W4402753640","https://openalex.org/W4402857029","https://openalex.org/W4292720242","https://openalex.org/W7133208581","https://openalex.org/W4378976853","https://openalex.org/W4316038852","https://openalex.org/W7168124556","https://openalex.org/W4387968064","https://openalex.org/W4405717810"],"abstract_inverted_index":{"Vision":[0,199],"Transformer":[1],"(ViT)":[2],"has":[3],"demonstrated":[4],"promising":[5],"performance":[6,82],"in":[7,33,54,99,120,149,226,235],"computer":[8,228],"vision":[9,229],"tasks,":[10],"comparable":[11,137],"to":[12,27,74,92,125,156,194],"state-of-the-art":[13],"neural":[14,22],"networks.":[15],"Yet,":[16],"this":[17,90,191,224],"new":[18],"type":[19,186],"of":[20,35,51,57,103,114,122,162,187,215,223],"deep":[21],"network":[23],"architecture":[24],"is":[25],"vulnerable":[26],"adversarial":[28,58,126,163],"attacks":[29,127],"limiting":[30],"its":[31],"capabilities":[32],"terms":[34,121],"robustness.":[36,84],"This":[37],"article":[38],"presents":[39],"a":[40,146,183,207],"novel":[41],"contribution":[42],"aimed":[43],"at":[44],"further":[45,233],"improving":[46,152,210],"the":[47,55,93,100,107,195,211,221],"accuracy":[48,129,178,212],"and":[49,83,128,179,213,231],"robustness":[50,124,180,214],"ViT,":[52,104],"particularly":[53],"face":[56],"attacks.":[59,164],"We":[60,110],"propose":[61],"an":[62],"augmentation":[63,142],"technique":[64,208],"called":[65],"\u2018Dynamic":[66],"Scanning":[67,116,175,204],"Augmentation\u2019":[68],"that":[69,89,173],"leverages":[70],"dynamic":[71],"input":[72,94],"sequences":[73],"adaptively":[75],"focus":[76],"on":[77,198],"different":[78,160],"patches,":[79],"thereby":[80],"maintaining":[81],"Our":[85],"detailed":[86],"investigations":[87],"reveal":[88],"adaptability":[91],"sequence":[95],"induces":[96],"significant":[97],"changes":[98],"attention":[101],"mechanism":[102],"even":[105],"for":[106,209],"same":[108],"image.":[109],"introduce":[111],"four":[112],"variations":[113],"Dynamic":[115,174,203],"Augmentation,":[117],"outperforming":[118],"ViT":[119],"both":[123],"against":[130],"natural":[131],"images,":[132],"with":[133,168],"one":[134],"variant":[135],"showing":[136],"results.":[138],"By":[139],"integrating":[140],"our":[141],"technique,":[143],"we":[144],"observe":[145],"substantial":[147],"increase":[148],"ViT\u2019s":[150],"robustness,":[151],"it":[153],"from":[154],"17%":[155],"92%":[157],"measured":[158],"across":[159],"types":[161],"These":[165],"findings,":[166],"together":[167],"other":[169],"comprehensive":[170],"tests,":[171],"indicate":[172],"Augmentation":[176,205],"enhances":[177],"by":[181,201],"promoting":[182],"more":[184],"adaptive":[185],"attention.":[188],"In":[189],"conclusion,":[190],"work":[192],"contributes":[193],"ongoing":[196],"research":[197],"Transformers":[200],"introducing":[202],"as":[206],"ViT.":[216],"The":[217],"observed":[218],"results":[219],"highlight":[220],"potential":[222],"approach":[225],"advancing":[227],"tasks":[230],"merit":[232],"exploration":[234],"future":[236],"studies.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-11-04T00:00:00"}