{"id":"https://openalex.org/W7169598040","doi":"https://doi.org/10.1109/access.2026.3714704","title":"Adversarial Training Foundations: Methods to Enhance Neural Network Robustness","display_name":"Adversarial Training Foundations: Methods to Enhance Neural Network Robustness","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7169598040","doi":"https://doi.org/10.1109/access.2026.3714704"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3714704","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3714704","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3714704","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008356532","display_name":"Jos\u00e9 Mar\u00eda Jorquera Valero","orcid":"https://orcid.org/0000-0003-1365-7573"},"institutions":[{"id":"https://openalex.org/I80180929","display_name":"Universidad de Murcia","ror":"https://ror.org/03p3aeb86","country_code":"ES","type":"education","lineage":["https://openalex.org/I80180929"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jose Maria Jorquera Valero","raw_affiliation_strings":["University of Murcia"],"raw_orcid":"https://orcid.org/0000-0003-1365-7573","affiliations":[{"raw_affiliation_string":"University of Murcia","institution_ids":["https://openalex.org/I80180929"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141069377","display_name":"Ibon Bengoechea Cazorla","orcid":null},"institutions":[{"id":"https://openalex.org/I80180929","display_name":"Universidad de Murcia","ror":"https://ror.org/03p3aeb86","country_code":"ES","type":"education","lineage":["https://openalex.org/I80180929"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ibon Bengoechea Cazorla","raw_affiliation_strings":["University of Murcia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Murcia","institution_ids":["https://openalex.org/I80180929"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033414840","display_name":"Manuel Gil P\u00e9rez","orcid":"https://orcid.org/0000-0002-7768-9665"},"institutions":[{"id":"https://openalex.org/I80180929","display_name":"Universidad de Murcia","ror":"https://ror.org/03p3aeb86","country_code":"ES","type":"education","lineage":["https://openalex.org/I80180929"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Manuel Gil Perez","raw_affiliation_strings":["University of Murcia"],"raw_orcid":"https://orcid.org/0000-0002-7768-9665","affiliations":[{"raw_affiliation_string":"University of Murcia","institution_ids":["https://openalex.org/I80180929"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I80180929"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.90592511,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"110122","last_page":"110138"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9768999814987183,"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":0.9768999814987183,"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":0.003800000064074993,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.002099999925121665,"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":0.7851999998092651},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7185999751091003},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6471999883651733},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5407999753952026},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4810999929904938},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.33379998803138733},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.32580000162124634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8212000131607056},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7851999998092651},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7185999751091003},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6471999883651733},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6292999982833862},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5407999753952026},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48410001397132874},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4810999929904938},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.33379998803138733},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.32580000162124634},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.305400013923645},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.28110000491142273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2773999869823456},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C47702885","wikidata":"https://www.wikidata.org/wiki/Q5441227","display_name":"Feedforward neural network","level":3,"score":0.26499998569488525},{"id":"https://openalex.org/C106516650","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm design","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3714704","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3714704","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:10778287adbd46389de479b2d7e65fa9","is_oa":false,"landing_page_url":"https://doaj.org/article/10778287adbd46389de479b2d7e65fa9","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 110122-110138 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3714704","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3714704","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G151569058","display_name":"SmaRt, AutOmated, and ReliaBle SecUrity Service PlaTform for 6G","funder_award_id":"101139068","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Adversarial":[0],"attacks":[1,33,42,149,196],"pose":[2],"a":[3,79,135,166],"significant":[4],"threat":[5],"to":[6,45,51,60,66,121,198,226],"the":[7,36,49,61,115,123,142,183,190,199,203,210,224],"reliability":[8],"and":[9,25,55,107,125,141,152,178,215,230],"security":[10],"of":[11,127,169],"Artificial":[12],"Intelligence":[13],"(AI)":[14],"systems,":[15],"especially":[16],"as":[17,220],"AI":[18],"integrates":[19],"into":[20],"critical":[21],"fields":[22],"like":[23,150],"healthcare":[24],"finance.":[26],"This":[27,118],"work":[28],"specifically":[29],"addresses":[30],"adversarial":[31,77,97,102,170],"evasion":[32],"conducted":[34,147],"during":[35,114],"testing":[37],"phase.":[38],"In":[39],"this":[40,74],"study,":[41],"are":[43,84,104,111,205],"designed":[44],"be":[46,218],"untargeted":[47,195],"(misleading":[48],"model":[50,132],"any":[52],"wrong":[53],"class)":[54],"white-box":[56],"(attacker":[57],"has":[58],"access":[59],"model),":[62],"using":[63,86,213],"small":[64],"perturbations":[65,110],"cause":[67],"incorrect":[68],"classifications.":[69],"To":[70],"counter":[71],"these":[72],"threats,":[73],"research":[75],"investigates":[76],"training,":[78],"defense":[80],"mechanism":[81],"where":[82,101,109],"models":[83],"trained":[85],"data":[87],"generated":[88,105],"by":[89],"attacks.":[90],"The":[91,163],"study":[92],"systematically":[93],"compares":[94],"two":[95],"distinct":[96],"training":[98,116,171],"strategies:":[99],"&#x2018;pre-train&#x2019;,":[100],"examples":[103],"beforehand,":[106],"&#x2018;in-train&#x2019;,":[108],"introduced":[112],"dynamically":[113],"process.":[117],"comparison":[119,168],"aims":[120],"understand":[122],"advantages":[124],"limitations":[126],"each":[128],"approach":[129],"in":[130,189],"enhancing":[131],"robustness.":[133],"Using":[134],"Fully":[136],"Connected":[137],"Neural":[138],"Network":[139],"(FCNN)":[140],"MNIST":[143,211],"dataset,":[144],"experiments":[145,208],"were":[146],"with":[148],"FGSM":[151],"BIM":[153],"at":[154],"varying":[155],"perturbation":[156],"strengths":[157],"<inline-formula>":[158],"<tex-math":[159],"notation=\"LaTeX\">$\\epsilon":[160],"$":[161],"</tex-math></inline-formula>.":[162],"results":[164],"provide":[165],"controlled":[167],"strategies,":[172],"highlighting":[173],"key":[174],"trade-offs":[175],"between":[176],"robustness":[177,188],"generalization.":[179],"We":[180],"observe":[181],"that":[182],"&#x2018;in-train&#x2019;":[184],"strategy":[185],"provides":[186],"superior":[187],"evaluated":[191],"setting":[192],"against":[193],"white-box,":[194],"compared":[197],"&#x2018;pre-train&#x2019;":[200],"method.":[201],"However,":[202],"findings":[204],"derived":[206],"from":[207],"on":[209],"dataset":[212],"FCNNs,":[214],"therefore":[216],"should":[217],"interpreted":[219],"foundational":[221],"insights.":[222],"Extending":[223],"analysis":[225],"more":[227],"complex":[228],"datasets":[229],"architectures":[231],"remains":[232],"an":[233],"important":[234],"direction":[235],"for":[236],"future":[237],"work.":[238]},"counts_by_year":[],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2026-07-18T00:00:00"}