Intrusion detection methods are crucial means to mitigate network security issues. However, the challenges posed by large-scale complex network environments include local information islands, regional privacy leaks, communication burdens, difficulties in handling heterogeneous data, and storage resource bottlenecks. Federated learning has the potential to address these challenges by leveraging widely distributed and heterogeneous data, achieving load balancing of storage and computing resources across multiple nodes, and reducing the risks of privacy leaks and bandwidth resource demands. This paper reviews the process of constructing federated learning based intrusion detection system from the perspective of intrusion detection. Specifically, it outlines six main aspects: application scenario analysis, federated learning methods, privacy and security protection, selection of classification models, data sources and client data distribution, and evaluation metrics, establishing them as key research content. Subsequently, six research topics are extracted based on these aspects. These topics include expanding application scenarios, enhancing aggregation algorithm, enhancing security, enhancing classification models, personalizing model and utilizing unlabeled data. Furthermore, the paper delves into research content related to each of these topics through in-depth investigation and analysis. Finally, the paper discusses the current challenges faced by research, and suggests promising directions for future exploration.
The incredible growth of Peer-to-Peer (P2P) networks has brought with it some complex challenges, such as trust issues and high bandwidth consumption. To address these challenges, this paper analyzes the “free-riding” behavior, system energy consumption, and the benefits of requesting and service peers in the network. A Geo/Geo/1+1 queuing model is built with malicious peers which includes several strategies such as repairable breakdown, synchronized multiple working vacations, differentiated service, and waiting threshold. The matrix-geometric solution method is used to obtain steady-state distribution and performance measures. By conducting numerical experiments and analyzing the impact of each parameter, it is possible to optimize the system's performance and reduce energy consumption. With careful adjustments to parameter values, significant cost savings of requesting peers and energy conservation can be achieved. The resulting analysis provides a comprehensive understanding of the behavior of P2P networks, and the strategies proposed in the study can be used to optimize the performance of P2P networks.