{"id":"https://openalex.org/W7165612292","doi":"https://doi.org/10.48550/arxiv.2606.22782","title":"Towards Robust Personalized Federated Learning: Vulnerability Assessment and Defense Co-Design","display_name":"Towards Robust Personalized Federated Learning: Vulnerability Assessment and Defense Co-Design","publication_year":2026,"publication_date":"2026-06-22","ids":{"openalex":"https://openalex.org/W7165612292","doi":"https://doi.org/10.48550/arxiv.2606.22782"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.22782","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22782","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.22782","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139174758","display_name":"Mingyuan Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Mingyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139163821","display_name":"Cen Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Cen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.7994999885559082,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.7994999885559082,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.149399995803833,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0071000000461936,"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/exploit","display_name":"Exploit","score":0.7544000148773193},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.7017999887466431},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.6736000180244446},{"id":"https://openalex.org/keywords/federated-learning","display_name":"Federated learning","score":0.5652999877929688},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4846000075340271},{"id":"https://openalex.org/keywords/adversarial-machine-learning","display_name":"Adversarial machine learning","score":0.4693000018596649},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.45809999108314514},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4302000105381012}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8055999875068665},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7544000148773193},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.7017999887466431},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.6736000180244446},{"id":"https://openalex.org/C2992525071","wikidata":"https://www.wikidata.org/wiki/Q50818671","display_name":"Federated learning","level":2,"score":0.5652999877929688},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4846000075340271},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.47350001335144043},{"id":"https://openalex.org/C2778403875","wikidata":"https://www.wikidata.org/wiki/Q20312394","display_name":"Adversarial machine learning","level":3,"score":0.4693000018596649},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.45809999108314514},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4302000105381012},{"id":"https://openalex.org/C167063184","wikidata":"https://www.wikidata.org/wiki/Q1400839","display_name":"Vulnerability assessment","level":3,"score":0.4196000099182129},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4002000093460083},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3522999882698059},{"id":"https://openalex.org/C46355384","wikidata":"https://www.wikidata.org/wiki/Q726686","display_name":"Compromise","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3156999945640564},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3028999865055084},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C140547941","wikidata":"https://www.wikidata.org/wiki/Q7797194","display_name":"Threat model","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.22782","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22782","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.22782","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22782","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"score":0.5598155856132507,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"proliferation":[1],"of":[2,14,37,167],"IoT":[3],"devices":[4],"has":[5],"fueled":[6],"distributed":[7],"edge":[8],"systems":[9],"to":[10,63,68,85,90,102,156],"collect":[11],"vast":[12],"amounts":[13],"sensitive":[15],"data,":[16,39],"creating":[17],"fertile":[18],"ground":[19],"for":[20],"on-device":[21],"machine":[22],"learning":[23,27,57,92],"applications.":[24],"While":[25],"federated":[26,56],"(FL)":[28],"mitigates":[29],"privacy":[30],"concerns":[31],"by":[32],"exchanging":[33],"model":[34,100],"parameters":[35],"instead":[36],"raw":[38],"we":[40,77,140],"identify":[41],"a":[42,142],"critical":[43],"blind":[44],"spot":[45],"in":[46,170],"current":[47],"research.":[48],"We":[49,113],"examine":[50],"the":[51,163],"most":[52],"commonly":[53],"used":[54],"personalized":[55,66,111],"(PFL)":[58],"methods,":[59],"which":[60],"allow":[61],"clients":[62,96],"maintain":[64],"private,":[65],"models":[67],"address":[69,137],"data":[70],"heterogeneity":[71],"across":[72,124,132],"clients.":[73],"Through":[74],"systematic":[75,165],"analysis,":[76],"reveal":[78],"that":[79,106],"PFL":[80,134,171],"methods":[81],"exhibit":[82],"heightened":[83],"vulnerability":[84,116],"transfer-based":[86],"adversarial":[87,104,168],"attacks":[88],"compared":[89],"centralized":[91],"paradigms.":[93],"Wherein,":[94],"malicious":[95],"can":[97,107],"exploit":[98],"local":[99],"knowledge":[101],"craft":[103],"examples":[105],"compromise":[108],"peer":[109],"clients'":[110],"models.":[112],"establish":[114,162],"this":[115,138],"through":[117],"both":[118,174],"theoretical":[119],"analysis":[120],"and":[121,152,177],"empirical":[122],"evaluation":[123],"multiple":[125],"benchmark":[126],"datasets,":[127],"demonstrating":[128],"significant":[129],"accuracy":[130],"drops":[131],"various":[133],"methods.":[135],"To":[136],"challenge,":[139],"propose":[141],"defense":[143],"framework":[144],"combining":[145],"stochastic":[146],"input":[147],"noise,":[148],"input-scaled":[149],"trace":[150],"regularization,":[151],"parameter":[153],"sensitivity":[154],"maximization":[155],"improve":[157],"FL's":[158],"robustness.":[159],"Our":[160],"findings":[161],"first":[164],"study":[166],"threats":[169],"systems,":[172],"providing":[173],"diagnostic":[175],"tools":[176],"practical":[178],"countermeasures.":[179]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-24T00:00:00"}