SenseCrypt clusters federated learning clients by data distribution using model parameter sensitivity, then assigns each client a straggler-free encryption budget and solves a knapsack-style mask selection to balance privacy and overhead.
The final aggregated model is decrypted once by the DKMS and then distributed to all clients
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
SenseCrypt: Sensitivity-guided Selective Homomorphic Encryption for Joint Federated Learning in Cross-Device Scenarios
SenseCrypt clusters federated learning clients by data distribution using model parameter sensitivity, then assigns each client a straggler-free encryption budget and solves a knapsack-style mask selection to balance privacy and overhead.