PA-iMFL: Communication-Efficient Privacy Amplification Method Against Data Reconstruction Attack in Improved Multilayer Federated Learning

Recently, big data has seen explosive growth in the Internet of Things (IoT). Multilayer FL (MFL) based on cloud-edge-end architecture can promote model training efficiency and model accuracy while preserving IoT data privacy. This article considers an improved MFL, where edge layer devices own private data and can join the training process. Improved MFL (iMFL) can improve edge resource utilization and also alleviate the strict requirement of end devices, but suffers from the issues of data reconstruction attack (DRA) and unacceptable communication overhead. This article aims to address these issues with iMFL. We propose a privacy amplification scheme on iMFL (PA-iMFL). Differing from standard MFL, we design privacy operations in end and edge devices after local training, including three sequential components, local differential privacy with Laplace mechanism, privacy amplification subsample, and gradient sign reset. Benefitting from privacy operations, PA-iMFL reduces communication overhead and achieves privacy preserving. Extensive results demonstrate that against state-of-the-art (SOTA) DRAs, PA-iMFL can effectively mitigate private data leakage and reach the same level of protection capability as the SOTA defense model. Moreover, due to adopting privacy operations in edge devices, PA-iMFL promotes up to
$2.8\times $
communication efficiency than the SOTA compression method without compromising model accuracy.