A New Solution to Intrusion Detection Systems Based on Improved Federated-Learning Chain

In the context of enterprise systems, intrusion detection (ID) emerges as a critical element driving the digital transformation of enterprises. With systems spanning various sectors of enterprises geographically dispersed, the necessity for seamless information exchange has surged significantly. The existing cross-domain solutions are challenged by such issues as insufficient security, high communication overhead, and a lack of effective update mechanisms, rendering them less feasible for prolonged application on resource-limited devices. This study proposes a new cross-domain collaboration scheme based on federated chains to streamline the server-side workload. Within this framework, individual nodes solely engage in training local data and subsequently amalgamate the final model employing a federated learning algorithm to uphold enterprise systems with efficiency and security. To curtail the resource utilization of blockchains and deter malicious nodes, a node administration module predicated on the workload paradigm is introduced, enabling the release of surplus resources in response to variations in a node’s contribution metric. Upon encountering an intrusion, the system triggers an alert and logs the characteristics of the breach, facilitating a comprehensive global update across all nodes for collective defense. Experimental results across multiple scenarios have verified the security and effectiveness of the proposed solution, with no loss of its recognition accuracy.