{"id":"https://openalex.org/W4414265937","doi":"https://doi.org/10.1109/tnse.2025.3610626","title":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","display_name":"Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networks","publication_year":2025,"publication_date":"2025-09-16","ids":{"openalex":"https://openalex.org/W4414265937","doi":"https://doi.org/10.1109/tnse.2025.3610626"},"language":"en","primary_location":{"id":"doi:10.1109/tnse.2025.3610626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnse.2025.3610626","pdf_url":null,"source":{"id":"https://openalex.org/S2484352698","display_name":"IEEE Transactions on Network Science and Engineering","issn_l":"2327-4697","issn":["2327-4697","2334-329X"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Network Science and Engineering","raw_type":"journal-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/A5102922010","display_name":"Yu Qiao","orcid":"https://orcid.org/0000-0003-4045-8473"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yu Qiao","raw_affiliation_strings":["School of Computing, Kyung Hee University, Yongin-si, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-4045-8473","affiliations":[{"raw_affiliation_string":"School of Computing, Kyung Hee University, Yongin-si, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021511574","display_name":"Apurba Adhikary","orcid":"https://orcid.org/0000-0003-3970-1878"},"institutions":[{"id":"https://openalex.org/I315729180","display_name":"Noakhali Science and Technology University","ror":"https://ror.org/05q9we431","country_code":"BD","type":"education","lineage":["https://openalex.org/I315729180"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Apurba Adhikary","raw_affiliation_strings":["Department of Information and Communication Engineering, Noakhali Science and Technology University, Noakhali, Bangladesh"],"raw_orcid":"https://orcid.org/0000-0003-3970-1878","affiliations":[{"raw_affiliation_string":"Department of Information and Communication Engineering, Noakhali Science and Technology University, Noakhali, Bangladesh","institution_ids":["https://openalex.org/I315729180"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685794","display_name":"Ki Tae Kim","orcid":"https://orcid.org/0000-0002-5692-1189"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kitae Kim","raw_affiliation_strings":["School of Computing, Kyung Hee University, Yongin-si, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-5692-1189","affiliations":[{"raw_affiliation_string":"School of Computing, Kyung Hee University, Yongin-si, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000263913","display_name":"Eui\u2010Nam Huh","orcid":"https://orcid.org/0000-0003-0184-6975"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Eui-Nam Huh","raw_affiliation_strings":["School of Computing, Kyung Hee University, Yongin-si, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-0184-6975","affiliations":[{"raw_affiliation_string":"School of Computing, Kyung Hee University, Yongin-si, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063667378","display_name":"Zhu Han","orcid":"https://orcid.org/0000-0002-6606-5822"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhu Han","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Houston, Houston, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-6606-5822","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034052371","display_name":"Choong Seon Hong","orcid":"https://orcid.org/0000-0003-3484-7333"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Choong Seon Hong","raw_affiliation_strings":["School of Computing, Kyung Hee University, Yongin-si, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-3484-7333","affiliations":[{"raw_affiliation_string":"School of Computing, Kyung Hee University, Yongin-si, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.188,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94295134,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"13","issue":null,"first_page":"2128","last_page":"2145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9868999719619751,"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":0.9868999719619751,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9674000144004822,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9542999863624573,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.8327999711036682},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.782800018787384},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.5809000134468079},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.5267999768257141},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.38449999690055847},{"id":"https://openalex.org/keywords/information-privacy","display_name":"Information privacy","score":0.3837999999523163},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.36579999327659607},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3610999882221222}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8327999711036682},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8029999732971191},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.782800018787384},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.5809000134468079},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.5267999768257141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4966000020503998},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48399999737739563},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4717000126838684},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4081000089645386},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.36579999327659607},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3366999924182892},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.329800009727478},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.3190000057220459},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.29350000619888306},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2833999991416931},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C10511746","wikidata":"https://www.wikidata.org/wiki/Q899388","display_name":"Data security","level":3,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tnse.2025.3610626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnse.2025.3610626","pdf_url":null,"source":{"id":"https://openalex.org/S2484352698","display_name":"IEEE Transactions on Network Science and Engineering","issn_l":"2327-4697","issn":["2327-4697","2334-329X"],"is_oa":false,"is_in_doaj":false,"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 Transactions on Network Science and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W2001610032","https://openalex.org/W2051267297","https://openalex.org/W2112796928","https://openalex.org/W2149466042","https://openalex.org/W2153086947","https://openalex.org/W2962814013","https://openalex.org/W2963542245","https://openalex.org/W2963857521","https://openalex.org/W2997560666","https://openalex.org/W3015735225","https://openalex.org/W3034537217","https://openalex.org/W3107235539","https://openalex.org/W3163105316","https://openalex.org/W3182158470","https://openalex.org/W3186626619","https://openalex.org/W3194922990","https://openalex.org/W3204341526","https://openalex.org/W3204874618","https://openalex.org/W3208693455","https://openalex.org/W3211999566","https://openalex.org/W4210580473","https://openalex.org/W4283796083","https://openalex.org/W4291972732","https://openalex.org/W4293846201","https://openalex.org/W4315646984","https://openalex.org/W4381734432","https://openalex.org/W4382237406","https://openalex.org/W4382318106","https://openalex.org/W4386075852","https://openalex.org/W4386076561","https://openalex.org/W4386453702","https://openalex.org/W4387146104","https://openalex.org/W4387968262","https://openalex.org/W4389352566","https://openalex.org/W4390872832","https://openalex.org/W4393099525","https://openalex.org/W4393230628","https://openalex.org/W4399336288","https://openalex.org/W4400032915","https://openalex.org/W4400679143","https://openalex.org/W4401665468","https://openalex.org/W4402159300","https://openalex.org/W4402667890","https://openalex.org/W4402703097","https://openalex.org/W4404787909","https://openalex.org/W4405022532","https://openalex.org/W4405175807","https://openalex.org/W4408164332","https://openalex.org/W4416228982"],"related_works":[],"abstract_inverted_index":{"Federated":[0,86],"learning":[1],"(FL)":[2],"is":[3,135],"a":[4,94,148],"distributed":[5],"training":[6,58,89,115],"paradigm":[7],"that":[8,53,222],"enhances":[9,186],"data":[10,18,29,74,124,131,182],"privacy":[11,75],"in":[12,37,104,230],"mobile":[13],"edge":[14,46],"networks":[15],"by":[16,109,142,181],"enabling":[17],"owners":[19],"to":[20,62,98,137,238],"collaboratively":[21],"train":[22],"models":[23],"without":[24],"sharing":[25],"raw":[26],"data.":[27],"However,":[28],"heterogeneity":[30,183],"and":[31,41,68,76,90,102,126,145,153,184,191],"adversarial":[32,57,114,140,154,163],"attacks":[33,141],"pose":[34],"significant":[35],"challenges":[36],"developing":[38],"an":[39,202],"unbiased":[40,171],"robust":[42],"global":[43,118,172,188],"model":[44],"for":[45],"deployment.":[47],"In":[48],"this":[49,82,108],"paper,":[50],"we":[51,84,194],"observe":[52],"most":[54],"existing":[55],"federated":[56],"frameworks":[59],"either":[60],"struggle":[61],"balance":[63],"the":[64,187,196,205],"trade-off":[65],"between":[66],"accuracy":[67,144,236],"robustness,":[69],"or":[70,226],"suffer":[71],"from":[72],"compromised":[73],"heavy":[77],"computational":[78],"overhead.":[79],"To":[80],"mitigate":[81],"problem,":[83],"propose":[85],"hyBrid":[87],"Adversarial":[88],"self-adversarial":[91],"disTillation":[92],"(FedBAT),":[93],"novel":[95],"framework":[96],"designed":[97],"improve":[99],"both":[100,123],"robustness":[101,146,190,232],"generalization":[103],"FL.":[105],"FedBAT":[106,200,223],"achieves":[107],"integrating":[110],"local":[111,162],"FL-based":[112],"hybrid":[113],"(FHAT)":[116],"with":[117,168],"augmentation-invariant":[119],"self-distillation":[120],"(AISD),":[121],"leveraging":[122],"augmentation":[125,132],"feature":[127,157,207],"distillation":[128,158],"perspectives.":[129],"From":[130,156],"perspective,":[133,159],"FHAT":[134],"employed":[136],"defend":[138],"against":[139],"balancing":[143],"through":[147,201],"weighted":[149],"combination":[150],"of":[151,165,199,204],"standard":[152],"training.":[155],"AISD":[160],"aligns":[161],"features":[164],"augmented":[166],"images":[167],"their":[169],"corresponding":[170],"clean":[173,235],"features.":[174],"This":[175],"feature-level":[176],"alignment":[177],"mitigates":[178],"bias":[179],"caused":[180],"further":[185,210],"model's":[189],"generalization.":[192],"Moreover,":[193],"interpret":[195],"performance":[197,228],"benefits":[198],"analysis":[203],"learned":[206],"distributions,":[208],"providing":[209],"insight":[211],"into":[212],"its":[213],"effectiveness.":[214],"Extensive":[215],"experimental":[216],"results":[217],"across":[218],"multiple":[219],"datasets":[220],"demonstrate":[221],"yields":[224],"comparable":[225],"superior":[227],"gains":[229],"improving":[231],"while":[233],"maintaining":[234],"compared":[237],"several":[239],"baselines.":[240]},"counts_by_year":[{"year":2025,"cited_by_count":3}],"updated_date":"2025-12-12T23:16:27.785689","created_date":"2025-10-10T00:00:00"}