Federated Learning with Differential Privacy
This work addresses privacy risks in federated learning for data-sensitive applications, but it is incremental as it provides empirical benchmarks rather than new methods.
The paper benchmarks how the number of clients and differential privacy mechanisms affect federated learning performance, finding that non-i.i.d. and small datasets suffer the highest performance decreases in such settings.
Federated learning (FL), as a type of distributed machine learning, is capable of significantly preserving client's private data from being shared among different parties. Nevertheless, private information can still be divulged by analyzing uploaded parameter weights from clients. In this report, we showcase our empirical benchmark of the effect of the number of clients and the addition of differential privacy (DP) mechanisms on the performance of the model on different types of data. Our results show that non-i.i.d and small datasets have the highest decrease in performance in a distributed and differentially private setting.