PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments

TL;DR

PPFL introduces a privacy-preserving federated learning framework using Trusted Execution Environments on clients and servers, effectively protecting models from attacks with minimal system overheads.

Contribution

The paper presents a novel PPFL framework leveraging TEEs for secure federated learning, including a greedy layer-wise training approach to address TEE memory limitations.

Findings

PPFL effectively defends against data reconstruction, property inference, and membership inference attacks.

Achieves comparable model utility with fewer communication rounds.

Introduces minimal system overheads in CPU, memory, and energy consumption.

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$\times$) and a similar amount of network traffic (1.002$\times$) 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.