Microgrids (MGs) have been equipped with large-scale distributed energy sources (DESs), and become more vulnerable due to the low inertia characteristic. In particular, high-density misbehaving DESs caused by cascading faults bring a great challenge to frequency synchronization and active power sharing among DESs. To tackle the problem, we propose a fully distributed resilient consensus protocol, which utilizes confidence weights to evaluate the level of trust among agents with a first-order filter and a softmax-type function. We pioneer the analysis of this nonlinear control system from the system operating range and the graph structure perspectives. Both necessary and sufficient conditions are provided to ensure DACC to be uniformly ultimately bounded, even in a robust network with low connectivity. Simulations on a modified IEEE33-bus microgrid testbed with 17 DESs validate that DACC outperforms existing methods in the presence of 8 misbehaving DESs.
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.