The Industrial Internet of Things (IIoT) increasingly relies on federated learning (FL) to enable collaborative model training without directly sharing raw traffic data across industrial sites. However, in practical IIoT deployments, clients may later request the removal of their data contributions from a trained federated model due to regulatory requirements, such as the General Data Protection Regulation (GDPR), ownership transfer, or internal data-governance policies. Such practical requirements create a strong demand for federated unlearning in IIoT applications. Furthermore, IIoT deployments often exhibit highly imbalanced client data distributions, resulting in substantially different contributions of individual clients to the global model. Nevertheless, most existing federated unlearning methods adopt a uniform unlearning strategy and fail to account for such client-level contribution gaps. To address this issue, we propose DynamicFU, a contribution-aware dynamic federated unlearning framework for IIoT deployments. The proposed method evaluates the target client from parameter-level, data-level, and performance-level perspectives and adaptively determines the unlearning strength by dynamically adjusting the number of unlearning rounds. Experimental results on public IIoT datasets show that DynamicFU substantially improves unlearning efficiency, achieving up to 22.89× speedup over Full Retrain while maintaining comparable effectiveness.

The continuous emergence of new attack classes challenges intrusion detection in edge Internet of Things (IoT) networks. Although federated learning enables distributed devices to collaboratively train a shared detector without exchanging raw traffic data, most federated intrusion detection systems assume a fixed label space. Retraining with all historical data incurs substantial storage and computation costs, whereas updating only with newly collected samples can cause catastrophic forgetting. The detector must mitigate catastrophic forgetting of previously observed attack classes while preserving sufficient new-class plasticity to learn emerging attacks under highly non-IID device data, intermittent client availability, constrained local memory, and repeated communication over bandwidth-limited and intermittently connected links. To address these challenges, this paper proposes EdgeFedCIL, a communication-efficient federated class-incremental intrusion detection framework. EdgeFedCIL preserves historical knowledge through client-local replay and knowledge distillation while reducing repeated model transmission through adaptive low-rank compression, quantization, and error feedback. A classifier-head protection strategy further limits compression-induced degradation of class discrimination. Experiments on public intrusion-detection datasets show that EdgeFedCIL achieves competitive or superior detection and historical-knowledge retention performance, particularly under highly heterogeneous client distributions, while reducing cumulative client-to-server model transmission by up to approximately 10.54 times relative to full-precision transmission. These results demonstrate the effectiveness of EdgeFedCIL for continual and communication-efficient intrusion detection in resource-constrained edge IoT networks.

Federated learning enables collaborative training across distributed sensor networks (DSNs) without requiring the sharing of raw sensing data. However, local updates can leak private information, and untrusted servers may return incorrect aggregation results. Existing verifiable secure aggregation schemes often incur high costs for resource-constrained devices. To address this, a verifiable and compressed FedAdam aggregation scheme (VCFedAdam) is proposesed. VCFedAdam performs masking, aggregation and verification operations within a low-dimensional sketch space, with the server recovering only the aggregated result for a fixed online set R, which consists of the users that successfully submit valid masked sketches in the current round and is fixed before aggregate recovery. Additionally, a commitment-bound verification (CBV) mechanism is designed to prevent the server from adaptively tampering with the aggregated results. At a compression ratio of $25\%$, experimental results show that VCFedAdam reduces computation overhead by $90.25\%$ and communication overhead by $75.38\%$ compared with traditional secure aggregation. On the CIFAR-10 and MNIST datasets, accuracy drops by only $0.64\%$ and $1.16\%$, respectively. Furthermore, security analysis confirms that VCFedAdam achieves both privacy protection and aggregation verifiability.