A Back Propagation Neural Network Intrusion Detection System Based on KVM

A Network Intrusion Detection System (NIDS) monitors a network for malicious activities or policy violations [1]. The Kernel-based Virtual Machine (KVM) is a full virtualization solution for Linux on x86 hardware virtualization extensions [2]. We design and implement a back-propagation network intrusion detection system in KVM. Compared to traditional Back Propagation (BP) NIDS, the Particle Swarm Optimization (PSO) algorithm is applied to improve efficiency. The results show an improved system in terms of recall and precision along with missing detection rates.