Hierarchical Federated Learning with Privacy

Recent work highlights how gradient-level access can lead to successful inference and reconstruction attacks against federated learning (FL). In such settings, differentially private (DP) learning is known to provide resilience. However, approaches used in the status quo (i.e., central and local DP) introduce disparate utility vs. privacy trade-offs. In this work, we mitigate such trade-offs through hierarchical FL (HFL). For the first time, we demonstrate that by the introduction of a new intermediary level where calibrated noise can be added, better trade-offs can be obtained; we term this hierarchical DP (HDP). Our experiments with 3 different datasets (commonly used as benchmarks for FL in prior works) suggest that HDP produces models as accurate as those obtained using central DP, where noise is added at a central aggregator at a lower privacy budget.