FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3117599504> ?p ?o ?g. }

• W3117599504 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.
• W3117599504 created "2021-01-05" @default.
• W3117599504 creator A5009102659 @default.
• W3117599504 creator A5032504910 @default.
• W3117599504 creator A5056811906 @default.
• W3117599504 creator A5057117256 @default.
• W3117599504 date "2020-12-27" @default.
• W3117599504 modified "2023-09-28" @default.
• W3117599504 title "FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping" @default.
• W3117599504 cites W134960717 @default.
• W3117599504 cites W2007562169 @default.
• W3117599504 cites W2033579026 @default.
• W3117599504 cites W2112507308 @default.
• W3117599504 cites W2149479912 @default.
• W3117599504 cites W2162552722 @default.
• W3117599504 cites W2194775991 @default.
• W3117599504 cites W2435090885 @default.
• W3117599504 cites W2535838896 @default.
• W3117599504 cites W2541884796 @default.
• W3117599504 cites W2613314732 @default.
• W3117599504 cites W2614254310 @default.
• W3117599504 cites W2748789698 @default.
• W3117599504 cites W2750384547 @default.
• W3117599504 cites W2752689052 @default.
• W3117599504 cites W2753783305 @default.
• W3117599504 cites W2774423163 @default.
• W3117599504 cites W2912099989 @default.
• W3117599504 cites W2946633206 @default.
• W3117599504 cites W2963165390 @default.
• W3117599504 cites W2963334472 @default.
• W3117599504 cites W2963343288 @default.
• W3117599504 cites W2963422767 @default.
• W3117599504 cites W2963777610 @default.
• W3117599504 cites W2963903822 @default.
• W3117599504 cites W2964043980 @default.
• W3117599504 cites W2964279249 @default.
• W3117599504 cites W2965497096 @default.
• W3117599504 cites W2970349186 @default.
• W3117599504 cites W2972594657 @default.
• W3117599504 cites W2973580531 @default.
• W3117599504 cites W2984488829 @default.
• W3117599504 cites W2985109970 @default.
• W3117599504 cites W2995164118 @default.
• W3117599504 cites W3012360060 @default.
• W3117599504 cites W3012737746 @default.
• W3117599504 cites W3012794253 @default.
• W3117599504 cites W3037024761 @default.
• W3117599504 cites W3043061209 @default.
• W3117599504 cites W3048715803 @default.
• W3117599504 cites W3101352448 @default.
• W3117599504 cites W3118608800 @default.
• W3117599504 cites W3167334189 @default.
• W3117599504 doi "https://doi.org/10.48550/arxiv.2012.13995" @default.
• W3117599504 hasPublicationYear "2020" @default.
• W3117599504 type Work @default.
• W3117599504 sameAs 3117599504 @default.
• W3117599504 citedByCount "5" @default.
• W3117599504 countsByYear W31175995042020 @default.
• W3117599504 countsByYear W31175995042021 @default.
• W3117599504 crossrefType "posted-content" @default.
• W3117599504 hasAuthorship W3117599504A5009102659 @default.
• W3117599504 hasAuthorship W3117599504A5032504910 @default.
• W3117599504 hasAuthorship W3117599504A5056811906 @default.
• W3117599504 hasAuthorship W3117599504A5057117256 @default.
• W3117599504 hasBestOaLocation W31175995041 @default.
• W3117599504 hasConcept C106159729 @default.
• W3117599504 hasConcept C116537 @default.
• W3117599504 hasConcept C119857082 @default.
• W3117599504 hasConcept C134306372 @default.
• W3117599504 hasConcept C136264566 @default.
• W3117599504 hasConcept C154945302 @default.
• W3117599504 hasConcept C162324750 @default.
• W3117599504 hasConcept C207609745 @default.
• W3117599504 hasConcept C26517878 @default.
• W3117599504 hasConcept C2780378061 @default.
• W3117599504 hasConcept C2992525071 @default.
• W3117599504 hasConcept C33923547 @default.
• W3117599504 hasConcept C34388435 @default.
• W3117599504 hasConcept C38652104 @default.
• W3117599504 hasConcept C41008148 @default.
• W3117599504 hasConceptScore W3117599504C106159729 @default.
• W3117599504 hasConceptScore W3117599504C116537 @default.
• W3117599504 hasConceptScore W3117599504C119857082 @default.
• W3117599504 hasConceptScore W3117599504C134306372 @default.
• W3117599504 hasConceptScore W3117599504C136264566 @default.
• W3117599504 hasConceptScore W3117599504C154945302 @default.
• W3117599504 hasConceptScore W3117599504C162324750 @default.
• W3117599504 hasConceptScore W3117599504C207609745 @default.
• W3117599504 hasConceptScore W3117599504C26517878 @default.
• W3117599504 hasConceptScore W3117599504C2780378061 @default.
• W3117599504 hasConceptScore W3117599504C2992525071 @default.
• W3117599504 hasConceptScore W3117599504C33923547 @default.
• W3117599504 hasConceptScore W3117599504C34388435 @default.
• W3117599504 hasConceptScore W3117599504C38652104 @default.
• W3117599504 hasConceptScore W3117599504C41008148 @default.
• W3117599504 hasLocation W31175995041 @default.
• W3117599504 hasOpenAccess W3117599504 @default.
• W3117599504 hasPrimaryLocation W31175995041 @default.
• W3117599504 hasRelatedWork W1486499954 @default.
• W3117599504 hasRelatedWork W2068931720 @default.

• next