Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387490548> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4387490548 endingPage "1" @default.
- W4387490548 startingPage "1" @default.
- W4387490548 abstract "Cross-device Federated Learning (FL) enables the privacy-preserving and collaborative training of machine learning models across heterogeneous clients. To prevent gradient information leakage, Homomorphic Encryption (HE) has been widely utilized due to its strong protection without losing accuracy. However, our experiments demonstrate that for clients with heterogeneous data and system capabilities, previous plain HE methods (i.e., encryption applied per gradient) and batch HE methods (i.e., encryption applied per batch of gradients) either significantly prolong training time or suffer from accuracy loss due to gradient quantization. We propose an adaptive batch HE framework for cross-device FL, which determines cost-efficient and sufficiently secure encryption strategies for clients with heterogeneous data and system capabilities. By leveraging the sparsity of Convolutional Neural Networks for privacy-preserving similarity measurement of clients’ data, we first split the clients with similar data into their respective clusters. Then, we develop a fuzzy logic based method to determine a cost-efficient and sufficiently secure HE key size for each client corresponding to its system capability, and arrange the clients with identical key size to the same groups. Finally, we design an efficient batch encryption approach for accuracy-lossless model aggregation. Extensive experiments on multiple heterogeneity scenarios demonstrate that our framework achieves comparable accuracy to plain HE, while reducing training time by 3×-31×, and communication cost by 45×-66×." @default.
- W4387490548 created "2023-10-11" @default.
- W4387490548 creator A5002890084 @default.
- W4387490548 creator A5030843666 @default.
- W4387490548 date "2023-01-01" @default.
- W4387490548 modified "2023-10-16" @default.
- W4387490548 title "Adaptive Batch Homomorphic Encryption for Joint Federated Learning in Cross-Device Scenarios" @default.
- W4387490548 doi "https://doi.org/10.1109/jiot.2023.3323358" @default.
- W4387490548 hasPublicationYear "2023" @default.
- W4387490548 type Work @default.
- W4387490548 citedByCount "0" @default.
- W4387490548 crossrefType "journal-article" @default.
- W4387490548 hasAuthorship W4387490548A5002890084 @default.
- W4387490548 hasAuthorship W4387490548A5030843666 @default.
- W4387490548 hasConcept C113775141 @default.
- W4387490548 hasConcept C11413529 @default.
- W4387490548 hasConcept C120314980 @default.
- W4387490548 hasConcept C124101348 @default.
- W4387490548 hasConcept C148730421 @default.
- W4387490548 hasConcept C153258448 @default.
- W4387490548 hasConcept C154945302 @default.
- W4387490548 hasConcept C158338273 @default.
- W4387490548 hasConcept C26517878 @default.
- W4387490548 hasConcept C28855332 @default.
- W4387490548 hasConcept C31258907 @default.
- W4387490548 hasConcept C38652104 @default.
- W4387490548 hasConcept C41008148 @default.
- W4387490548 hasConcept C50644808 @default.
- W4387490548 hasConcept C78548338 @default.
- W4387490548 hasConcept C79403827 @default.
- W4387490548 hasConcept C81081738 @default.
- W4387490548 hasConceptScore W4387490548C113775141 @default.
- W4387490548 hasConceptScore W4387490548C11413529 @default.
- W4387490548 hasConceptScore W4387490548C120314980 @default.
- W4387490548 hasConceptScore W4387490548C124101348 @default.
- W4387490548 hasConceptScore W4387490548C148730421 @default.
- W4387490548 hasConceptScore W4387490548C153258448 @default.
- W4387490548 hasConceptScore W4387490548C154945302 @default.
- W4387490548 hasConceptScore W4387490548C158338273 @default.
- W4387490548 hasConceptScore W4387490548C26517878 @default.
- W4387490548 hasConceptScore W4387490548C28855332 @default.
- W4387490548 hasConceptScore W4387490548C31258907 @default.
- W4387490548 hasConceptScore W4387490548C38652104 @default.
- W4387490548 hasConceptScore W4387490548C41008148 @default.
- W4387490548 hasConceptScore W4387490548C50644808 @default.
- W4387490548 hasConceptScore W4387490548C78548338 @default.
- W4387490548 hasConceptScore W4387490548C79403827 @default.
- W4387490548 hasConceptScore W4387490548C81081738 @default.
- W4387490548 hasFunder F4320321001 @default.
- W4387490548 hasFunder F4320335777 @default.
- W4387490548 hasLocation W43874905481 @default.
- W4387490548 hasOpenAccess W4387490548 @default.
- W4387490548 hasPrimaryLocation W43874905481 @default.
- W4387490548 hasRelatedWork W2539930818 @default.
- W4387490548 hasRelatedWork W2917767146 @default.
- W4387490548 hasRelatedWork W2949835517 @default.
- W4387490548 hasRelatedWork W3012147850 @default.
- W4387490548 hasRelatedWork W3183118997 @default.
- W4387490548 hasRelatedWork W3204296682 @default.
- W4387490548 hasRelatedWork W3204400881 @default.
- W4387490548 hasRelatedWork W3214410901 @default.
- W4387490548 hasRelatedWork W4285609037 @default.
- W4387490548 hasRelatedWork W4313300189 @default.
- W4387490548 isParatext "false" @default.
- W4387490548 isRetracted "false" @default.
- W4387490548 workType "article" @default.