Aggregating Gradients in Encoded Domain for Federated Learning

05/26/2022
by   Dun Zeng, et al.
0

Malicious attackers and an honest-but-curious server can steal private client data from uploaded gradients in federated learning. Although current protection methods (e.g., additive homomorphic cryptosystem) can guarantee the security of the federated learning system, they bring additional computation and communication costs. To mitigate the cost, we propose the framework, which enables the server to aggregate gradients in an encoded domain without accessing raw gradients of any single client. Thus, can prevent the curious server from gradient stealing while maintaining the same prediction performance without additional communication costs. Furthermore, we theoretically prove that the proposed encoding-decoding framework is a Gaussian mechanism for differential privacy. Finally, we evaluate under several federated settings, and the results have demonstrated the efficacy of the proposed framework.

READ FULL TEXT

page 8

page 18

research
07/12/2022

Efficient and Privacy Preserving Group Signature for Federated Learning

Federated Learning (FL) is a Machine Learning (ML) technique that aims t...
research
02/26/2021

Efficient Client Contribution Evaluation for Horizontal Federated Learning

In federated learning (FL), fair and accurate measurement of the contrib...
research
08/22/2019

An End-to-End Encrypted Neural Network for Gradient Updates Transmission in Federated Learning

Federated learning is a distributed learning method to train a shared mo...
research
12/26/2022

LOCKS: User Differentially Private and Federated Optimal Client Sampling

With changes in privacy laws, there is often a hard requirement for clie...
research
04/19/2020

Local Differential Privacy based Federated Learning for Internet of Things

Internet of Vehicles (IoV) is a promising branch of the Internet of Thin...
research
06/01/2022

Optimization with access to auxiliary information

We investigate the fundamental optimization question of minimizing a tar...
research
05/19/2022

FedILC: Weighted Geometric Mean and Invariant Gradient Covariance for Federated Learning on Non-IID Data

Federated learning is a distributed machine learning approach which enab...

Please sign up or login with your details

Forgot password? Click here to reset