Quality-Aware and Incentive-Boosted Federated Learning with Differential Privacy
A novel quality-aware and incentive-boosted federated learning framework based on ρ-zero-concentrated differential privacy (ρ-zCDP) to incentivize participation of mobile devices with high-quality data and eliminate privacy threats associated with gradient disclosure.
Differentially Private Federated Learning: Challenges in High-Dimensional Estimation and Inference under Untrusted Servers
In high-dimensional settings, accurate estimation is not feasible under the untrusted central server constraint in federated learning, even for simple sparse mean estimation problems. However, in the trusted central server setting, novel algorithms can achieve near-optimal estimation and inference results.
Differentially Private Federated Learning Mechanism using Correlated Binary Stochastic Quantization
The CorBin-FL and AugCorBin-FL mechanisms achieve differential privacy guarantees in federated learning by using correlated binary stochastic quantization of local model updates.
