{"id":"https://openalex.org/W7225655869","doi":"https://doi.org/10.3390/electronics15215187","title":"Fed-PriLoRA: A Synergistic Framework for Private and Robust Federated Low-Rank Adaptation","display_name":"Fed-PriLoRA: A Synergistic Framework for Private and Robust Federated Low-Rank Adaptation","publication_year":2026,"publication_date":"2026-11-08","ids":{"openalex":"https://openalex.org/W7225655869","doi":"https://doi.org/10.3390/electronics15215187"},"language":"en","primary_location":{"id":"doi:10.3390/electronics15215187","doi":"https://doi.org/10.3390/electronics15215187","is_oa":true,"landing_page_url":"https://doi.org/10.3390/electronics15215187","pdf_url":null,"source":{"id":"https://openalex.org/S4210202905","display_name":"Electronics","issn_l":"2079-9292","issn":["2079-9292"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronics","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/electronics15215187","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110008675","display_name":"Dan Lv","orcid":"https://orcid.org/0009-0009-7281-0540","observed_orcids":["https://orcid.org/0009-0009-7281-0540"]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Lv","raw_affiliation_strings":["School of Cybersecurity, Northwestern Polytechnical University, Xi\u2019an 710072, China"],"raw_orcid":"https://orcid.org/0009-0009-7281-0540","affiliations":[{"raw_affiliation_string":"School of Cybersecurity, Northwestern Polytechnical University, Xi\u2019an 710072, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5159785468","display_name":"Zeyuan Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zeyuan Wang","raw_affiliation_strings":["School of Cybersecurity, Northwestern Polytechnical University, Xi\u2019an 710072, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cybersecurity, Northwestern Polytechnical University, Xi\u2019an 710072, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5159785468"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2896},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2896},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"21","first_page":"5187","last_page":"5187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.0,"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/federated-learning","display_name":"federated learning","score":0.9580000042915344},{"id":"https://openalex.org/keywords/lora","display_name":"LoRa","score":0.7379999756813049},{"id":"https://openalex.org/keywords/low-rank-adaptation","display_name":"low-rank adaptation","score":0.8650000095367432},{"id":"https://openalex.org/keywords/differential-privacy","display_name":"differential privacy","score":0.9369999766349792},{"id":"https://openalex.org/keywords/llm-fine-tuning","display_name":"LLM fine-tuning","score":0.8209999799728394},{"id":"https://openalex.org/keywords/privacy-preserving-federated-learning","display_name":"privacy-preserving federated learning","score":0.6299999952316284},{"id":"https://openalex.org/keywords/fisher-information","display_name":"Fisher information","score":0.9789999723434448},{"id":"https://openalex.org/keywords/parameter-importance","display_name":"parameter importance","score":0.6389999985694885},{"id":"https://openalex.org/keywords/communication-efficiency","display_name":"communication efficiency","score":0.6620000004768372}],"concepts":[{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.8514999747276306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.718999981880188},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5871000289916992},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5631999969482422},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5404999852180481},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.47200000286102295},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4404999911785126},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.42089998722076416},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C2779208394","wikidata":"https://www.wikidata.org/wiki/Q7140460","display_name":"Participatory sensing","level":2,"score":0.3772999942302704},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36959999799728394},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C18015164","wikidata":"https://www.wikidata.org/wiki/Q6935000","display_name":"Multiplicative noise","level":5,"score":0.3529999852180481},{"id":"https://openalex.org/C137822555","wikidata":"https://www.wikidata.org/wiki/Q2587068","display_name":"Information sensitivity","level":2,"score":0.34769999980926514},{"id":"https://openalex.org/C32022120","wikidata":"https://www.wikidata.org/wiki/Q797225","display_name":"Interference (communication)","level":3,"score":0.3127000033855438},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.31060001254081726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30799999833106995},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C29406490","wikidata":"https://www.wikidata.org/wiki/Q1420659","display_name":"Fisher information","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C2780821482","wikidata":"https://www.wikidata.org/wiki/Q25381721","display_name":"Crowdsensing","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.28200000524520874},{"id":"https://openalex.org/C2780909371","wikidata":"https://www.wikidata.org/wiki/Q4801092","display_name":"Artificial noise","level":4,"score":0.27459999918937683},{"id":"https://openalex.org/C179145077","wikidata":"https://www.wikidata.org/wiki/Q5154130","display_name":"Communication complexity","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.25949999690055847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/electronics15215187","doi":"https://doi.org/10.3390/electronics15215187","is_oa":true,"landing_page_url":"https://doi.org/10.3390/electronics15215187","pdf_url":null,"source":{"id":"https://openalex.org/S4210202905","display_name":"Electronics","issn_l":"2079-9292","issn":["2079-9292"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/electronics15215187","doi":"https://doi.org/10.3390/electronics15215187","is_oa":true,"landing_page_url":"https://doi.org/10.3390/electronics15215187","pdf_url":null,"source":{"id":"https://openalex.org/S4210202905","display_name":"Electronics","issn_l":"2079-9292","issn":["2079-9292"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","poland-100","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Electronics","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321106","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2594311007","https://openalex.org/W4388953041","https://openalex.org/W4394874608","https://openalex.org/W4396882204","https://openalex.org/W4401545746","https://openalex.org/W4404601267","https://openalex.org/W4404792929","https://openalex.org/W4405601061","https://openalex.org/W4410393192","https://openalex.org/W4412939506","https://openalex.org/W4415795789","https://openalex.org/W7083286760","https://openalex.org/W7131381104","https://openalex.org/W7222970262"],"related_works":["https://openalex.org/W4393027113","https://openalex.org/W7196950502","https://openalex.org/W7131408901","https://openalex.org/W7214093124","https://openalex.org/W7124817570","https://openalex.org/W7160616803","https://openalex.org/W4414711821","https://openalex.org/W4401545746","https://openalex.org/W4417051888","https://openalex.org/W7131381104"],"abstract_inverted_index":{"Utilizing":[0],"federated":[1],"learning":[2],"to":[3,55,96,113,124,134,139,172],"fine-tune":[4],"large":[5],"language":[6],"models":[7],"on":[8,154],"sensitive":[9],"private":[10],"data":[11],"while":[12],"achieving":[13],"strong":[14],"privacy":[15,40,61,102],"protection":[16],"without":[17],"sacrificing":[18],"model":[19],"utility":[20],"remains":[21],"a":[22,188],"fundamental":[23],"challenge.":[24],"Although":[25],"parameter-efficient":[26],"fine-tuning":[27],"methods":[28],"such":[29],"as":[30],"LoRA":[31],"significantly":[32],"reduce":[33],"communication":[34,143,164,168],"overhead,":[35],"integrating":[36],"them":[37],"with":[38],"differential":[39,101],"introduces":[41],"issues":[42],"including":[43],"multiplicative":[44,98],"noise":[45,48,118,136],"amplification,":[46],"cross-round":[47],"accumulation,":[49],"and":[50,74,104,158],"consequent":[51],"training":[52],"instability,":[53],"leading":[54],"severe":[56],"performance":[57],"degradation":[58],"under":[59],"strict":[60],"constraints.":[62],"To":[63],"address":[64],"the":[65,71,128,150,156,166],"above":[66],"challenges,":[67],"this":[68],"paper":[69],"proposes":[70],"Fed-PriLoRA":[72,145],"(Private":[73],"Robust":[75],"Federated":[76],"Low-Rank":[77],"Adaptation)":[78],"framework.":[79],"The":[80],"framework":[81],"decomposes":[82],"each":[83],"client\u2019s":[84],"low-rank":[85],"update":[86],"into":[87],"separable":[88],"vector":[89],"pairs.":[90],"It":[91],"then":[92],"employs":[93],"structured":[94],"freezing":[95],"suppress":[97],"amplification":[99],"of":[100,163,175,192],"noise,":[103],"leverages":[105],"Fisher":[106,122],"information":[107,123],"for":[108],"noise-aware":[109],"parameter":[110,126],"importance":[111],"evaluation":[112],"distinguish":[114],"generalizable":[115],"features":[116],"from":[117],"interference.":[119],"By":[120],"using":[121],"assess":[125],"importance,":[127],"client":[129],"locally":[130],"discards":[131],"low-contribution":[132],"components":[133],"mitigate":[135],"interference":[137],"prior":[138],"uploading,":[140],"thereby":[141],"reducing":[142],"overhead.":[144],"achieves":[146],"higher":[147],"accuracy":[148,190],"than":[149],"non-private":[151],"StackLoRA":[152],"baseline":[153],"both":[155],"Dolly-15K":[157],"WizardLM":[159],"datasets.":[160],"In":[161],"terms":[162],"efficiency,":[165],"per-round":[167],"overhead":[169],"is":[170],"reduced":[171],"just":[173],"0.051%":[174],"that":[176,184],"incurred":[177],"in":[178],"full":[179],"fine-tuning.":[180],"Ablation":[181],"experiments":[182],"demonstrate":[183],"Fisher-guided":[185],"pruning":[186],"yields":[187],"relative":[189],"increase":[191],"39%":[193],"over":[194],"random":[195],"pruning.":[196]},"counts_by_year":[],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2026-11-10T00:00:00"}