English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recently, big data has seen explosive growth in the Internet of Things (IoT).Multi-layer FL (MFL) based on cloud-edge-end architecture can promote modeltraining efficiency and model accuracy while preserving IoT data privacy. Thispaper considers an improved MFL, where edge layer devices own private data andcan join the training process. iMFL can improve edge resource utilization andalso alleviate the strict requirement of end devices, but suffers from theissues of Data Reconstruction Attack (DRA) and unacceptable communicationoverhead. This paper aims to address these issues with iMFL. We propose aPrivacy Amplification scheme on iMFL (PA-iMFL). Differing from standard MFL, wedesign privacy operations in end and edge devices after local training,including three sequential components, local differential privacy with Laplacemechanism, privacy amplification subsample, and gradient sign reset.Benefitting from privacy operations, PA-iMFL reduces communication overhead andachieves privacy-preserving. Extensive results demonstrate that againstState-Of-The-Art (SOTA) DRAs, PA-iMFL can effectively mitigate private dataleakage and reach the same level of protection capability as the SOTA defensemodel. Moreover, due to adopting privacy operations in edge devices, PA-iMFLpromotes up to 2.8 times communication efficiency than the SOTA compressionmethod without compromising model accuracy.

PA-iMFL: Communication-Efficient Privacy Amplification Method against Data Reconstruction Attack in Improved Multi-Layer Federated Learning