PPFL

TLDR

The authors propose a Privacy‑Preserving Federated Learning framework for mobile systems to reduce privacy leakage in federated learning. The framework employs Trusted Execution Environments on clients for local training and on servers for secure aggregation, using greedy layer‑wise training to fit each model layer within the limited TEE memory until convergence. Evaluation shows PPFL significantly improves privacy, defends against data reconstruction, property inference, and membership inference attacks, while achieving comparable model utility with 0.54× fewer communication rounds, similar traffic, and only ~15% CPU, ~18% memory, and ~21% energy overhead.

Abstract

We propose and implement a Privacy-preserving Federated Learning (PPFL) framework for mobile systems to limit privacy leakages in federated learning. Leveraging the widespread presence of Trusted Execution Environments (TEEs) in high-end and mobile devices, we utilize TEEs on clients for local training, and on servers for secure aggregation, so that model/gradient updates are hidden from adversaries. Challenged by the limited memory size of current TEEs, we leverage greedy layer-wise training to train each model's layer inside the trusted area until its convergence. The performance evaluation of our implementation shows that PPFL can significantly improve privacy while incurring small system overheads at the client-side. In particular, PPFL can successfully defend the trained model against data reconstruction, property inference, and membership inference attacks. Furthermore, it can achieve comparable model utility with fewer communication rounds (0.54×) and a similar amount of network traffic (1.002×) compared to the standard federated learning of a complete model. This is achieved while only introducing up to ~15% CPU time, ~18% memory usage, and ~21% energy consumption overhead in PPFL's client-side.