Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382052893> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4382052893 abstract "Differential privacy is an essential tool in federated learning privacy preservation. However, existing differential privacy-preserving techniques introduce excessive noise perturbations for privacy-preserving purposes, which makes federated learning models less usable. Under the condition of satisfying differential privacy, this paper proposes a new noise addition method, differential privacy preservation by federated learning based on differentiated noise addition (DDPFL), to reduce the loss of model usability. Specifically, the method derives importance coefficients for each model parameter by analyzing the value of the gradient update size, the magnitude of the absolute value of the weight parameter, and the relationship between the global model and the local model gradient update trend during the training process for each client. Then, noise is added to the model parameters using a differentiated noise addition mechanism according to the magnitude of the importance coefficients to achieve noise perturbation of the local model. Finally, the effectiveness of the proposed method is validated by an experimental comparison of the MNIST dataset and the Fashion-Mnist dataset. The usability of the model improves under the same differential privacy condition as the federated learning differential privacy preserving method before the improvement." @default.
- W4382052893 created "2023-06-27" @default.
- W4382052893 creator A5011407484 @default.
- W4382052893 creator A5037286379 @default.
- W4382052893 creator A5056993032 @default.
- W4382052893 creator A5081477195 @default.
- W4382052893 date "2023-04-26" @default.
- W4382052893 modified "2023-09-30" @default.
- W4382052893 title "Federated Learning Differential Privacy Preservation Method Based on Differentiated Noise Addition" @default.
- W4382052893 cites W2982464076 @default.
- W4382052893 cites W3016632787 @default.
- W4382052893 cites W3020949888 @default.
- W4382052893 cites W3091476023 @default.
- W4382052893 cites W3203723547 @default.
- W4382052893 doi "https://doi.org/10.1109/icccbda56900.2023.10154864" @default.
- W4382052893 hasPublicationYear "2023" @default.
- W4382052893 type Work @default.
- W4382052893 citedByCount "0" @default.
- W4382052893 crossrefType "proceedings-article" @default.
- W4382052893 hasAuthorship W4382052893A5011407484 @default.
- W4382052893 hasAuthorship W4382052893A5037286379 @default.
- W4382052893 hasAuthorship W4382052893A5056993032 @default.
- W4382052893 hasAuthorship W4382052893A5081477195 @default.
- W4382052893 hasConcept C107457646 @default.
- W4382052893 hasConcept C108583219 @default.
- W4382052893 hasConcept C111919701 @default.
- W4382052893 hasConcept C115961682 @default.
- W4382052893 hasConcept C124101348 @default.
- W4382052893 hasConcept C127413603 @default.
- W4382052893 hasConcept C136764020 @default.
- W4382052893 hasConcept C146978453 @default.
- W4382052893 hasConcept C154945302 @default.
- W4382052893 hasConcept C170130773 @default.
- W4382052893 hasConcept C190502265 @default.
- W4382052893 hasConcept C23130292 @default.
- W4382052893 hasConcept C2780615836 @default.
- W4382052893 hasConcept C41008148 @default.
- W4382052893 hasConcept C93226319 @default.
- W4382052893 hasConcept C98045186 @default.
- W4382052893 hasConcept C99498987 @default.
- W4382052893 hasConceptScore W4382052893C107457646 @default.
- W4382052893 hasConceptScore W4382052893C108583219 @default.
- W4382052893 hasConceptScore W4382052893C111919701 @default.
- W4382052893 hasConceptScore W4382052893C115961682 @default.
- W4382052893 hasConceptScore W4382052893C124101348 @default.
- W4382052893 hasConceptScore W4382052893C127413603 @default.
- W4382052893 hasConceptScore W4382052893C136764020 @default.
- W4382052893 hasConceptScore W4382052893C146978453 @default.
- W4382052893 hasConceptScore W4382052893C154945302 @default.
- W4382052893 hasConceptScore W4382052893C170130773 @default.
- W4382052893 hasConceptScore W4382052893C190502265 @default.
- W4382052893 hasConceptScore W4382052893C23130292 @default.
- W4382052893 hasConceptScore W4382052893C2780615836 @default.
- W4382052893 hasConceptScore W4382052893C41008148 @default.
- W4382052893 hasConceptScore W4382052893C93226319 @default.
- W4382052893 hasConceptScore W4382052893C98045186 @default.
- W4382052893 hasConceptScore W4382052893C99498987 @default.
- W4382052893 hasLocation W43820528931 @default.
- W4382052893 hasOpenAccess W4382052893 @default.
- W4382052893 hasPrimaryLocation W43820528931 @default.
- W4382052893 hasRelatedWork W2167735388 @default.
- W4382052893 hasRelatedWork W2276478028 @default.
- W4382052893 hasRelatedWork W2891542592 @default.
- W4382052893 hasRelatedWork W2892911634 @default.
- W4382052893 hasRelatedWork W2904174853 @default.
- W4382052893 hasRelatedWork W2947175736 @default.
- W4382052893 hasRelatedWork W3156786002 @default.
- W4382052893 hasRelatedWork W4287510235 @default.
- W4382052893 hasRelatedWork W4309224979 @default.
- W4382052893 hasRelatedWork W4382052893 @default.
- W4382052893 isParatext "false" @default.
- W4382052893 isRetracted "false" @default.
- W4382052893 workType "article" @default.