{"id":"https://openalex.org/W7123868849","doi":"https://doi.org/10.1109/ojcs.2025.3650722","title":"A Validation Strategy for Deep Learning Models: Evaluating and Enhancing Robustness","display_name":"A Validation Strategy for Deep Learning Models: Evaluating and Enhancing Robustness","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7123868849","doi":"https://doi.org/10.1109/ojcs.2025.3650722"},"language":null,"primary_location":{"id":"doi:10.1109/ojcs.2025.3650722","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2025.3650722","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","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/ojcs.2025.3650722","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047883853","display_name":"Abdul-Rauf Nuhu","orcid":null},"institutions":[{"id":"https://openalex.org/I35777872","display_name":"North Carolina Agricultural and Technical State University","ror":"https://ror.org/02aze4h65","country_code":"US","type":"education","lineage":["https://openalex.org/I35777872"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abdul-Rauf Nuhu","raw_affiliation_strings":["Department of Electrical, Computer Engineering, North Carolina A&amp;T State University, Greensboro, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer Engineering, North Carolina A&amp;T State University, Greensboro, NC, USA","institution_ids":["https://openalex.org/I35777872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088897776","display_name":"Parham M. Kebria","orcid":"https://orcid.org/0000-0001-7049-928X"},"institutions":[{"id":"https://openalex.org/I35777872","display_name":"North Carolina Agricultural and Technical State University","ror":"https://ror.org/02aze4h65","country_code":"US","type":"education","lineage":["https://openalex.org/I35777872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Parham M. Kebria","raw_affiliation_strings":["Department of Electrical, Computer Engineering, North Carolina A&amp;T State University, Greensboro, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer Engineering, North Carolina A&amp;T State University, Greensboro, NC, USA","institution_ids":["https://openalex.org/I35777872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093279939","display_name":"Vahid Hemmati","orcid":null},"institutions":[{"id":"https://openalex.org/I35777872","display_name":"North Carolina Agricultural and Technical State University","ror":"https://ror.org/02aze4h65","country_code":"US","type":"education","lineage":["https://openalex.org/I35777872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vahid Hemmati","raw_affiliation_strings":["Department of Electrical, Computer Engineering, North Carolina A&amp;T State University, Greensboro, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer Engineering, North Carolina A&amp;T State University, Greensboro, NC, USA","institution_ids":["https://openalex.org/I35777872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006858330","display_name":"Benjamin Lartey","orcid":"https://orcid.org/0000-0002-7094-8919"},"institutions":[{"id":"https://openalex.org/I35777872","display_name":"North Carolina Agricultural and Technical State University","ror":"https://ror.org/02aze4h65","country_code":"US","type":"education","lineage":["https://openalex.org/I35777872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Lartey","raw_affiliation_strings":["Department of Electrical, Computer Engineering, North Carolina A&amp;T State University, Greensboro, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer Engineering, North Carolina A&amp;T State University, Greensboro, NC, USA","institution_ids":["https://openalex.org/I35777872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018554930","display_name":"Mahmoud Nabil","orcid":"https://orcid.org/0000-0003-3059-7912"},"institutions":[{"id":"https://openalex.org/I17301866","display_name":"University of Alabama","ror":"https://ror.org/03xrrjk67","country_code":"US","type":"education","lineage":["https://openalex.org/I17301866"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahmoud Nabil Mahmoud","raw_affiliation_strings":["Department of Computer Science, University of Alabama, Tuscaloosa, AL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Alabama, Tuscaloosa, AL, USA","institution_ids":["https://openalex.org/I17301866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054416654","display_name":"Abdollah Homaifar","orcid":"https://orcid.org/0000-0003-1179-3221"},"institutions":[{"id":"https://openalex.org/I35777872","display_name":"North Carolina Agricultural and Technical State University","ror":"https://ror.org/02aze4h65","country_code":"US","type":"education","lineage":["https://openalex.org/I35777872"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdollah Homaifar","raw_affiliation_strings":["Department of Electrical, Computer Engineering, North Carolina A&amp;T State University, Greensboro, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical, Computer Engineering, North Carolina A&amp;T State University, Greensboro, NC, USA","institution_ids":["https://openalex.org/I35777872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006027872","display_name":"Edward Tunstel","orcid":"https://orcid.org/0000-0001-7023-9170"},"institutions":[{"id":"https://openalex.org/I1290463931","display_name":"Southwest Research Institute","ror":"https://ror.org/03tghng59","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1290463931"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Edward Tunstel","raw_affiliation_strings":["Southwest Research Institute, San Antonio, TX, USA"],"affiliations":[{"raw_affiliation_string":"Southwest Research Institute, San Antonio, TX, USA","institution_ids":["https://openalex.org/I1290463931"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5047883853"],"corresponding_institution_ids":["https://openalex.org/I35777872"],"apc_list":{"value":1750,"currency":"USD","value_usd":1750},"apc_paid":{"value":1750,"currency":"USD","value_usd":1750},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18963777,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"7","issue":null,"first_page":"276","last_page":"289"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9810000061988831,"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":0.9810000061988831,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.008200000040233135,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.002300000051036477,"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/robustness","display_name":"Robustness (evolution)","score":0.8855000138282776},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7166000008583069},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6229000091552734},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.47940000891685486},{"id":"https://openalex.org/keywords/model-validation","display_name":"Model validation","score":0.4383000135421753},{"id":"https://openalex.org/keywords/robustness-testing","display_name":"Robustness testing","score":0.40619999170303345}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8855000138282776},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7166000008583069},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7131999731063843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6890000104904175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6421999931335449},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6229000091552734},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.47940000891685486},{"id":"https://openalex.org/C3019813237","wikidata":"https://www.wikidata.org/wiki/Q65089264","display_name":"Model validation","level":2,"score":0.4383000135421753},{"id":"https://openalex.org/C137726913","wikidata":"https://www.wikidata.org/wiki/Q7353550","display_name":"Robustness testing","level":3,"score":0.40619999170303345},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3896999955177307},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35600000619888306},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ojcs.2025.3650722","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2025.3650722","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/ojcs.2025.3650722","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ojcs.2025.3650722","pdf_url":null,"source":{"id":"https://openalex.org/S4210176459","display_name":"IEEE Open Journal of the Computer Society","issn_l":"2644-1268","issn":["2644-1268"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Open Journal of the Computer Society","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7843424081802368}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1892947258","https://openalex.org/W2117539524","https://openalex.org/W2180612164","https://openalex.org/W2302255633","https://openalex.org/W2474835145","https://openalex.org/W2543927648","https://openalex.org/W2566079294","https://openalex.org/W2767471303","https://openalex.org/W2774644650","https://openalex.org/W2902543210","https://openalex.org/W2954996726","https://openalex.org/W2963446712","https://openalex.org/W2963542245","https://openalex.org/W2964137095","https://openalex.org/W3037492894","https://openalex.org/W3108655343","https://openalex.org/W3144874349","https://openalex.org/W3184424762","https://openalex.org/W3210224281","https://openalex.org/W4207085178","https://openalex.org/W4293846201","https://openalex.org/W4312349930","https://openalex.org/W4313731376","https://openalex.org/W4328028516","https://openalex.org/W4388574628","https://openalex.org/W4388757885","https://openalex.org/W4400104927","https://openalex.org/W4404132873","https://openalex.org/W4404411894","https://openalex.org/W4404688056","https://openalex.org/W4405179357","https://openalex.org/W4405520473","https://openalex.org/W4407690503"],"related_works":[],"abstract_inverted_index":{"Data-driven":[0],"models,":[1],"especially":[2],"deep":[3],"learning":[4],"classifiers":[5],"often":[6],"demonstrate":[7,122],"great":[8],"success":[9],"on":[10,47,102,128],"clean":[11],"datasets.":[12],"Yet,":[13],"they":[14],"remain":[15],"vulnerable":[16],"to":[17,51,86],"common":[18,25,155],"data":[19],"distortions":[20],"such":[21],"as":[22,89],"adversarial":[23,153],"and":[24,53,92,134,154],"corruption":[26,156],"perturbations.":[27],"These":[28,80],"perturbations":[29],"can":[30,145],"significantly":[31],"degrade":[32],"performance,":[33],"thereby":[34],"challenging":[35,104],"the":[36,40,73,83,96,123],"overall":[37],"reliability":[38,151],"of":[39,95,113,125],"models.":[41],"Traditional":[42],"robustness":[43,78,138],"validation":[44,64,139],"typically":[45],"relies":[46],"perturbed":[48],"test":[49],"datasets":[50],"assess":[52],"improve":[54],"model":[55,150],"performance.":[56],"In":[57],"our":[58,126],"framework,":[59],"however,":[60],"we":[61,107],"propose":[62],"a":[63,109],"approach":[65,127],"that":[66],"extracts":[67],"\u201cweak":[68],"robust\u201d":[69],"samples":[70,144],"directly":[71],"from":[72],"training":[74,105],"dataset":[75],"via":[76],"local":[77],"analysis.":[79],"samples,":[81],"being":[82],"most":[84],"susceptible":[85],"perturbations,":[87],"serve":[88],"an":[90],"early":[91],"sensitive":[93],"indicator":[94],"model's":[97],"vulnerabilities.":[98],"By":[99],"evaluating":[100],"models":[101,129],"these":[103],"instances,":[106],"gain":[108],"more":[110],"nuanced":[111],"understanding":[112],"its":[114],"robustness,":[115],"which":[116],"informs":[117],"targeted":[118],"performance":[119],"enhancement.":[120],"We":[121],"effectiveness":[124],"trained":[130],"with":[131],"CIFAR-10,":[132],"CIFAR-100,":[133],"ImageNet,":[135],"highlighting":[136],"how":[137],"guided":[140],"by":[141],"weak":[142],"robust":[143],"drive":[146],"meaningful":[147],"improvements":[148],"in":[149],"under":[152],"scenarios.":[157]},"counts_by_year":[],"updated_date":"2026-01-22T23:29:09.771500","created_date":"2026-01-14T00:00:00"}
