With the increasing severity of network security issues, traditional network security strategies are no longer able to cope with various advanced, sustained, and complex network attacks. Therefore, the stability and security of the network environment have become issues that need to be taken seriously. This paper is dedicated to the study of the Computer Network Security Monitoring System using ML algorithms, and through its performance test and malicious code intrusion test. In system vulnerability monitoring, the accuracy of the Computer Network Security Monitoring System of the proposed algorithm is up to 98.5%, and the lowest false detection rate is 0.33%. The accuracy rate of the network security system based on source code slicing is up to 98.3%. The minimum false detection rate is 2.52%. The results show that the system in this article has strong performance and can more effectively identify and prevent network attacks, thereby preventing the intrusion of malicious code and improving the security and stability of the network.