{"id":"https://openalex.org/W7108324296","doi":"https://doi.org/10.36227/techrxiv.176472698.88480884/v1","title":"Adversarial Robustness in Federated Learning for Safety-Critical Healthcare IoT Systems","display_name":"Adversarial Robustness in Federated Learning for Safety-Critical Healthcare IoT Systems","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W7108324296","doi":"https://doi.org/10.36227/techrxiv.176472698.88480884/v1"},"language":"en","primary_location":{"id":"doi:10.36227/techrxiv.176472698.88480884/v1","doi":"https://doi.org/10.36227/techrxiv.176472698.88480884/v1","is_oa":true,"landing_page_url":"https://doi.org/10.36227/techrxiv.176472698.88480884/v1","pdf_url":"https://www.techrxiv.org/doi/pdf/10.36227/techrxiv.176472698.88480884","source":null,"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":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.techrxiv.org/doi/pdf/10.36227/techrxiv.176472698.88480884","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001847870","display_name":"Ayodeji Oseni","orcid":"https://orcid.org/0000-0001-6535-8730","observed_orcids":["https://orcid.org/0000-0001-6535-8730"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ayodeji Oseni","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-6535-8730","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080095540","display_name":"Peter W. Vamplew","orcid":"https://orcid.org/0000-0002-8687-4424","observed_orcids":["https://orcid.org/0000-0002-8687-4424"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Vamplew","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013402425","display_name":"Cameron Foale","orcid":"https://orcid.org/0000-0003-2537-0326","observed_orcids":["https://orcid.org/0000-0003-2537-0326"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cameron Foale","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5025207179","display_name":"Mehdi Naseriparsa","orcid":"https://orcid.org/0000-0001-9230-1625","observed_orcids":["https://orcid.org/0000-0001-9230-1625"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mehdi Naseriparsa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5001847870"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5576000213623047,"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":0.5576000213623047,"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":0.43970000743865967,"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/T10270","display_name":"Blockchain Technology Applications and Security","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/federated-learning","display_name":"federated learning","score":0.8889999985694885},{"id":"https://openalex.org/keywords/adversarial-robustness","display_name":"adversarial robustness","score":0.9950000047683716},{"id":"https://openalex.org/keywords/internet-of-medical-things","display_name":"Internet of Medical Things","score":0.953000009059906},{"id":"https://openalex.org/keywords/safety-critical-systems","display_name":"safety-critical systems","score":0.7950000166893005},{"id":"https://openalex.org/keywords/backdoor-attacks","display_name":"backdoor attacks","score":0.8659999966621399},{"id":"https://openalex.org/keywords/label-flipping-attacks","display_name":"label-flipping attacks","score":0.984000027179718},{"id":"https://openalex.org/keywords/byzantine-robust-aggregation","display_name":"Byzantine-robust aggregation","score":0.9539999961853027},{"id":"https://openalex.org/keywords/median-aggregation","display_name":"median aggregation","score":0.7540000081062317},{"id":"https://openalex.org/keywords/krum","display_name":"Krum","score":0.7139999866485596},{"id":"https://openalex.org/keywords/diabetes-mellitus","display_name":"diabetes mellitus","score":0.5389999747276306},{"id":"https://openalex.org/keywords/continuous-glucose-monitoring","display_name":"continuous glucose monitoring","score":0.9079999923706055},{"id":"https://openalex.org/keywords/insulin-pump","display_name":"insulin pump","score":0.7919999957084656},{"id":"https://openalex.org/keywords/patient-safety","display_name":"patient safety","score":0.675000011920929}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7426999807357788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7120000123977661},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.6880000233650208},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6568999886512756},{"id":"https://openalex.org/C160735492","wikidata":"https://www.wikidata.org/wiki/Q31207","display_name":"Health care","level":2,"score":0.6187999844551086},{"id":"https://openalex.org/C2988170871","wikidata":"https://www.wikidata.org/wiki/Q11000047","display_name":"Healthcare system","level":3,"score":0.5424000024795532},{"id":"https://openalex.org/C81860439","wikidata":"https://www.wikidata.org/wiki/Q251212","display_name":"Internet of Things","level":2,"score":0.5268999934196472},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.44909998774528503},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37549999356269836},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.31150001287460327},{"id":"https://openalex.org/C2779582901","wikidata":"https://www.wikidata.org/wiki/Q21013010","display_name":"Distributed learning","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C3017977704","wikidata":"https://www.wikidata.org/wiki/Q18745135","display_name":"Health data","level":3,"score":0.27790001034736633},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.27379998564720154},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C145642194","wikidata":"https://www.wikidata.org/wiki/Q870895","display_name":"Health informatics","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C19527686","wikidata":"https://www.wikidata.org/wiki/Q1665453","display_name":"System integration","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.36227/techrxiv.176472698.88480884/v1","doi":"https://doi.org/10.36227/techrxiv.176472698.88480884/v1","is_oa":true,"landing_page_url":"https://doi.org/10.36227/techrxiv.176472698.88480884/v1","pdf_url":"https://www.techrxiv.org/doi/pdf/10.36227/techrxiv.176472698.88480884","source":null,"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":"posted-content"}],"best_oa_location":{"id":"doi:10.36227/techrxiv.176472698.88480884/v1","doi":"https://doi.org/10.36227/techrxiv.176472698.88480884/v1","is_oa":true,"landing_page_url":"https://doi.org/10.36227/techrxiv.176472698.88480884/v1","pdf_url":"https://www.techrxiv.org/doi/pdf/10.36227/techrxiv.176472698.88480884","source":null,"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":"posted-content"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","display_name":"Good health and well-being","score":0.6240000128746033}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7108324296.pdf","grobid_xml":"https://content.openalex.org/works/W7108324296.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2900120080","https://openalex.org/W3046183292","https://openalex.org/W3137164102","https://openalex.org/W4386096129","https://openalex.org/W4415145354"],"related_works":["https://openalex.org/W7147382753","https://openalex.org/W7160560896","https://openalex.org/W7130733873","https://openalex.org/W7161575456","https://openalex.org/W7171559581","https://openalex.org/W7135368101","https://openalex.org/W4416750992","https://openalex.org/W7221913954","https://openalex.org/W7166644010","https://openalex.org/W7127932287"],"abstract_inverted_index":{"Federated":[0],"learning":[1,6],"(FL)":[2],"enables":[3],"collaborative":[4],"machine":[5],"across":[7],"distributed":[8,36],"healthcare":[9,21,60,94,265],"institutions":[10],"while":[11,240],"preserving":[12],"patient":[13,53],"data":[14,114,129,141],"privacy,":[15],"making":[16],"it":[17],"particularly":[18],"valuable":[19],"for":[20,147,155,258,277],"IoT":[22,95,266],"systems":[23,96],"that":[24,43,196,252],"underpin":[25],"critical":[26,50,257],"social":[27],"infrastructure":[28],"such":[29,98],"as":[30,215],"digital":[31],"health":[32],"services.":[33],"However,":[34],"its":[35,275],"nature":[37],"introduces":[38],"vulnerabilities":[39,169],"to":[40,52,159,179],"adversarial":[41,89],"attacks":[42,176],"can":[44],"compromise":[45],"model":[46,149],"accuracy":[47],"and":[48,55,110,126,151,162,188,213],"pose":[49],"risks":[51],"safety":[54],"public":[56],"trust":[57],"in":[58,82,93,170,183,201,264,282],"AI-enabled":[59],"systems.":[61,267],"These":[62],"threats":[63],"are":[64],"further":[65,205],"intensified":[66],"by":[67],"server-side":[68],"uncertainty,":[69],"where":[70],"aggregation":[71,208,224,255,273],"servers":[72],"cannot":[73],"reliably":[74],"assess":[75,206],"client":[76],"trustworthiness":[77],"or":[78],"detect":[79],"malicious":[80],"activity":[81],"real":[83],"time.":[84],"This":[85],"paper":[86],"evaluates":[87],"the":[88,117,259],"robustness":[90],"of":[91,193,262,271],"FL":[92,263],"under":[97],"realistic":[99],"uncertainty":[100],"conditions.":[101],"We":[102,204],"examine":[103],"three":[104],"key":[105],"attack":[106],"vectors-backdoor,":[107],"label":[108,238],"flipping,":[109,239],"gradient":[111,174,229],"manipulation":[112,175,230],"attacks-using":[113],"derived":[115],"from":[116,130,142],"DiaTrend":[118],"dataset,":[119],"which":[120],"comprises":[121],"continuous":[122],"glucose":[123],"monitor":[124],"(CGM)":[125],"insulin":[127],"pump":[128],"54":[131],"patients":[132],"with":[133],"diabetes.":[134],"For":[135],"our":[136],"experimental":[137],"evaluation,":[138],"we":[139],"utilized":[140],"12":[143],"subjects:":[144],"10":[145],"subjects":[146,154],"federated":[148,172,279],"training":[150],"2":[152],"held-out":[153],"independent":[156],"performance":[157,220,236],"validation":[158],"ensure":[160],"robust":[161],"generalizable":[163],"results.":[164],"Experimental":[165],"findings":[166,250],"reveal":[167],"severe":[168],"standard":[171],"averaging:":[173],"caused":[177],"up":[178],"a":[180],"3,145%":[181],"increase":[182],"mean":[184],"squared":[185],"error":[186],"(MSE)":[187],"an":[189],"average":[190],"prediction":[191],"deviation":[192],"79.1":[194],"mg/dL-levels":[195],"represent":[197],"potentially":[198],"life-threatening":[199],"errors":[200],"clinical":[202],"contexts.":[203],"Byzantine-robust":[207,254],"methods":[209],"(Krum,":[210],"Trimmed":[211,232],"Mean,":[212],"Median)":[214],"proactive,":[216],"attack-agnostic":[217],"defenses.":[218],"Defense":[219],"varies":[221],"substantially:":[222],"Median":[223,272],"achieves":[225,242],"94.4%":[226],"recovery":[227],"against":[228,237,246],"attacks,":[231],"Mean":[233],"nearly":[234],"restores":[235],"Krum":[241],"only":[243],"4.2%":[244],"mitigation":[245],"backdoor":[247],"attacks.":[248],"Our":[249],"highlight":[251],"proactive":[253],"is":[256],"safe":[260],"deployment":[261],"The":[268],"exceptional":[269],"resilience":[270],"demonstrates":[274],"viability":[276],"secure":[278],"CGM":[280],"analytics":[281],"safety-critical":[283],"applications.":[284]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2025-12-03T00:00:00"}