Balancing Privacy Protection and Interpretability in Federated Learning

Understand

Federated learning (FL) aims to collaboratively train the global model in a distributed manner by sharing the model parameters from local clients to a central server, thereby potentially protecting users' private information.

• Nevertheless, recent studies have illustrated that FL still suffers from information leakage as adversaries try to recover the training data by analyzing shared parameters from local clients.
• To deal with this issue, differential privacy (DP) is adopted to add noise to the gradients of local models before aggregation.
• It, however, results in the poor performance of gradient-based interpretability methods, since some weights capturing the salient region in feature map will be perturbed.