Can I read Compressed Federated Learning Based on Adaptive Local Differential Privacy on EtoBox?

Compressed Federated Learning Based on Adaptive Local Differential Privacy by Yinbin Miao; Rongpeng Xie; Xinghua Li; Ximeng Liu; Zhuo Ma; Robert H. Deng is a scholarly article available to read on EtoBox.

What is Compressed Federated Learning Based on Adaptive Local Differential Privacy about?

Federated learning (FL) was once considered secure for keeping clients' raw data locally without relaying on a central server. However, the transmitted model weights or gradients still reveal private information, which can be exploited to launch various inference attacks. Moreover, FL based on deep neural networks is prone to the curse of dimensionality. In this paper, we propose a compressed and privacy-preserving FL scheme in DNN architecture by using Compressive sensing and Adaptive local differential privacy (called as CAFL). Specifically, we first compress the local models by using Compressive Sensing (CS), then adaptively perturb the remaining weights according to their different centers of variation ranges in different layers and their own offsets from corresponding range centers by using Local Differential Privacy (LDP), finally reconstruct the global model almost perfectly by using the reconstruction algorithm of CS. Formal security analysis shows that our scheme achieves ε-LDP security and introduces zero bias to estimating average weights. Extensive experiments using MINIST and Fashion-MINIST datasets demonstrate that our scheme with minimum compression ratio 0.05 can re

Author

Yinbin Miao; Rongpeng Xie; Xinghua Li; Ximeng Liu; Zhuo Ma; Robert H. Deng

Publisher

ACM

Published

2022

Language

EN