Design and Research of Network Edge Device Security Monitoring System Based on Embedded System and Bi-LSTM

With the popularization of smart devices and networked devices, edge device security issues have become increasingly prominent. Traditional security monitoring systems often rely on centralized data processing mode, which is difficult to meet the current real-time analysis requirements of massive data. In order to solve this problem, this paper designs a network edge device security monitoring system based on the fusion of embedded system and bidirectional long-short-term memory network. By deploying the Bi-LSTM model through the embedded processor, the system can detect the abnormal behavior of edge devices in real time, thereby improving the response speed and accuracy of security monitoring. This paper conducts experimental analysis on the actual network traffic data set, collects security data from different types of edge devices, covering device types including smart routers, IoT sensors, etc., and processes more than 100GB of network traffic data in total. The experimental results show that the detection accuracy of the Bi-LSTM model in network attack behavior reaches 96.8%, which is about 4.2% and 5.5% higher than the traditional random forest and support vector machine models respectively. In addition, the real-time analysis of the system shows that the average processing latency of the embedded system is less than 200 ms, which meets the low latency requirement in edge computing environment.