Application KCFM to Detect New P2P Botnet Based on Multi-Observed Sequence

We propose a novel real-time detecting model-KCFM(Kalman filter and multi-chart CUSUM fused model) based on multi-observed sequence,which consists of several extracted the new P2P botnet characteristic properties.The KCFM finds the abnormal traffic by the discrete Kalman filter,and improves the detection precision by using the Multi-chart CUSUM as an amplifier.The experiments show that our approach can detect new decentralized botnet with a relatively high precision.