Utility-Enhanced Personalized Privacy Preservation in Hierarchical Federated Learning

Federated learning (FL) is a distributed learning framework that allows clients to jointly train a model by uploading parameter updates rather than sharing local data. FL deployed on a client-edge-cloud hierarchical architecture, named Hierarchical Federated Learning (HFL), can accelerate model training and accommodate more clients with reduced communication cost via edge aggregation. Unfortunately, HFL suffers from privacy risks since the submitted parameters from clients are vulnerable to privacy attacks. To address this issue, we propose a novel Differential Privacy (DP) definition tailored for HFL, i.e., Group Local Differential Privacy (GLDP). We design the Sampling-Randomizing-Shuffling (SRS) mechanism to implement GLDP in HFL, where the sampling process is employed to achieve a stronger level of privacy protection with less noise added. By combining the randomized response and the shuffling mechanism, our proposed SRS mechanism can achieve client-level personalization within $\rho _{k}$-GLDP for privacy preservation while balancing model performance and privacy protection in HFL. Privacy analysis and convergence analysis are conducted to provide theoretical performance guarantees. Experimental results based on real-world datasets verify the effectiveness of SRS.