Journal Article

Symmetry-Aware Byzantine Resilience in Federated Learning via Dual-Channel Attention-Driven Anomaly Detection

Zhang, Yuliang, Hou, Jian, Luo, Xianyu, Wang, Lili, Zhou, Xianke, Ruan, Linjie

2026

Overview

Byzantine failures remain a critical threat to Federated Learning (FL), where malicious clients inject adversarial updates to disrupt global model convergence. From the perspective of symmetry, benign client updates typically exhibit statistical symmetry around the global consensus, whereas Byzantine attacks function as “symmetry-breaking” events that introduce skewness and distributional anomalies. Existing defenses often rely on unrealistic assumptions or fail to capture these asymmetric deviations under high-dimensional non-IID settings. In this paper, we propose a symmetry-aware Byzantine-resilient FL framework driven by a Dual-Channel Attention-Driven Anomaly Detector (DAAD). Specifically, DAAD transforms inter-client behaviors into geometrically symmetric interaction matrices—encoding Gradient Cosine Similarities and Loss Euclidean Distances—to construct dual-channel spatial representations. These representations are processed via a Convolutional Neural Network (CNN) enhanced with Squeeze-and-Excitation (SE) attention blocks, which leverage the inherent symmetry of benign consensus to extract robust adversarial signatures. The detector is pre-trained offline on a synthetic dataset incorporating a diverse portfolio of simulated attacks (e.g., Gaussian noise and label flipping). Crucially, this pre-trained model is seamlessly embedded into the online FL loop to filter updates without requiring ground-truth labels. By jointly encoding client behaviors and learning cross-modal attack signatures, our framework enables reliable detection even when over half of the clients are Byzantine. Extensive experiments on MNIST, CIFAR-10, and FEMNIST datasets demonstrate that DAAD consistently outperforms existing robust aggregation baselines in both anomaly detection accuracy and global model performance, especially under high Byzantine ratios and non-IID conditions.

• Publisher: MDPI AG
• Subject: Anomalies / Artificial neural networks / Attention / Broken symmetry / Clients / Coding / Communication / Datasets / Detectors / Evaluation / Federated learning / Investment analysis / Labels / Machine learning / Neural networks / Poisoning / Privacy / Random noise / Representations / Resilience / Robustness / Semantics / Sensors / Statistical methods / Symmetry / Synthetic data / Trust