An Adaptive Differential Private Federated Learning in Secure IoT

IoT technology shortens the last mile to access various data around human's life and promotes the data-driven intelligence. Meanwhile, it brings about several security problems. Federated learning (FL) is proposed as a privacy-preserving learning paradigm. However, existing works show that FL is vulnerable to adversarial attacks. Against these attacks, differential privacy (DP) is regarded as one of the effective defenses. However, the existing DP-enabled FL works largely neglect the heterogeneity of participants in terms of protecting privacy. In this paper, we propose an adaptive DP-enabled FL (ADPFL). We are motivated by the heterogeneity resulting from non-iid distributions and associate the different privacy budgets with participants' important parameters. Then, we assign different Laplacian mechanisms with different participants to generate different noises that perturb the uploaded gradients. Finally, we produce an ADPFL framework. We conduct extensive experiments to verify the effectiveness of our ADPFL.