FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3138597937> ?p ?o ?g. }

• W3138597937 abstract "Byzantine-robust federated learning aims to enable a service provider to learn an accurate global model when a bounded number of clients are malicious. The key idea of existing Byzantine-robust federated learning methods is that the service provider performs statistical analysis among the clients' local model updates and removes suspicious ones, before aggregating them to update the global model. However, malicious clients can still corrupt the global models in these methods via sending carefully crafted local model updates to the service provider. The fundamental reason is that there is no root of trust in existing federated learning methods. In this work, we bridge the gap via proposing FLTrust, a new federated learning method in which the service provider itself bootstraps trust. In particular, the service provider itself collects a clean small training dataset (called root dataset) for the learning task and the service provider maintains a model (called server model) based on it to bootstrap trust. In each iteration, the service provider first assigns a trust score to each local model update from the clients, where a local model update has a lower trust score if its direction deviates more from the direction of the server model update. Then, the service provider normalizes the magnitudes of the local model updates such that they lie in the same hyper-sphere as the server model update in the vector space. Our normalization limits the impact of malicious local model updates with large magnitudes. Finally, the service provider computes the average of the normalized local model updates weighted by their trust scores as a global model update, which is used to update the global model. Our extensive evaluations on six datasets from different domains show that our FLTrust is secure against both existing attacks and strong adaptive attacks." @default.
• W3138597937 created "2021-03-29" @default.
• W3138597937 creator A5009102659 @default.
• W3138597937 creator A5032504910 @default.
• W3138597937 creator A5056811906 @default.
• W3138597937 creator A5057117256 @default.
• W3138597937 date "2021-01-01" @default.
• W3138597937 modified "2023-10-16" @default.
• W3138597937 title "FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping" @default.
• W3138597937 doi "https://doi.org/10.14722/ndss.2021.24434" @default.
• W3138597937 hasPublicationYear "2021" @default.
• W3138597937 type Work @default.
• W3138597937 sameAs 3138597937 @default.
• W3138597937 citedByCount "71" @default.
• W3138597937 countsByYear W31385979372020 @default.
• W3138597937 countsByYear W31385979372021 @default.
• W3138597937 countsByYear W31385979372022 @default.
• W3138597937 countsByYear W31385979372023 @default.
• W3138597937 crossrefType "proceedings-article" @default.
• W3138597937 hasAuthorship W3138597937A5009102659 @default.
• W3138597937 hasAuthorship W3138597937A5032504910 @default.
• W3138597937 hasAuthorship W3138597937A5056811906 @default.
• W3138597937 hasAuthorship W3138597937A5057117256 @default.
• W3138597937 hasBestOaLocation W31385979371 @default.
• W3138597937 hasConcept C104562893 @default.
• W3138597937 hasConcept C120314980 @default.
• W3138597937 hasConcept C149782125 @default.
• W3138597937 hasConcept C154945302 @default.
• W3138597937 hasConcept C166957645 @default.
• W3138597937 hasConcept C168021876 @default.
• W3138597937 hasConcept C207609745 @default.
• W3138597937 hasConcept C2992525071 @default.
• W3138597937 hasConcept C33923547 @default.
• W3138597937 hasConcept C41008148 @default.
• W3138597937 hasConcept C63540848 @default.
• W3138597937 hasConcept C95457728 @default.
• W3138597937 hasConceptScore W3138597937C104562893 @default.
• W3138597937 hasConceptScore W3138597937C120314980 @default.
• W3138597937 hasConceptScore W3138597937C149782125 @default.
• W3138597937 hasConceptScore W3138597937C154945302 @default.
• W3138597937 hasConceptScore W3138597937C166957645 @default.
• W3138597937 hasConceptScore W3138597937C168021876 @default.
• W3138597937 hasConceptScore W3138597937C207609745 @default.
• W3138597937 hasConceptScore W3138597937C2992525071 @default.
• W3138597937 hasConceptScore W3138597937C33923547 @default.
• W3138597937 hasConceptScore W3138597937C41008148 @default.
• W3138597937 hasConceptScore W3138597937C63540848 @default.
• W3138597937 hasConceptScore W3138597937C95457728 @default.
• W3138597937 hasLocation W31385979371 @default.
• W3138597937 hasLocation W31385979372 @default.
• W3138597937 hasOpenAccess W3138597937 @default.
• W3138597937 hasPrimaryLocation W31385979371 @default.
• W3138597937 hasRelatedWork W1548189724 @default.
• W3138597937 hasRelatedWork W2002589180 @default.
• W3138597937 hasRelatedWork W2034320198 @default.
• W3138597937 hasRelatedWork W2149625404 @default.
• W3138597937 hasRelatedWork W2763042189 @default.
• W3138597937 hasRelatedWork W3129381981 @default.
• W3138597937 hasRelatedWork W3210293592 @default.
• W3138597937 hasRelatedWork W4220997590 @default.
• W3138597937 hasRelatedWork W4252331942 @default.
• W3138597937 hasRelatedWork W635625959 @default.
• W3138597937 isParatext "false" @default.
• W3138597937 isRetracted "false" @default.
• W3138597937 magId "3138597937" @default.
• W3138597937 workType "article" @default.