Byzantine-Robust Federated Learning via Credibility Assessment on Non-IID Data

TL;DR

This paper introduces BRCA, a credibility assessment framework that enhances Byzantine robustness in federated learning on non-iid data by combining adaptive anomaly detection and data verification.

Contribution

It proposes a novel credibility assessment approach with an adaptive anomaly detection model and a unified update algorithm for non-iid federated learning.

Findings

BRCA outperforms conventional methods in robustness against Byzantine attacks.

The adaptive anomaly detection improves attack detection accuracy.

The unified update ensures consistent global model convergence.

Abstract

Federated learning is a novel framework that enables resource-constrained edge devices to jointly learn a model, which solves the problem of data protection and data islands. However, standard federated learning is vulnerable to Byzantine attacks, which will cause the global model to be manipulated by the attacker or fail to converge. On non-iid data, the current methods are not effective in defensing against Byzantine attacks. In this paper, we propose a Byzantine-robust framework for federated learning via credibility assessment on non-iid data (BRCA). Credibility assessment is designed to detect Byzantine attacks by combing adaptive anomaly detection model and data verification. Specially, an adaptive mechanism is incorporated into the anomaly detection model for the training and prediction of the model. Simultaneously, a unified update algorithm is given to guarantee that the global model has a consistent direction. On non-iid data, our experiments demonstrate that the BRCA is more robust to Byzantine attacks compared with conventional methods