Hybrid Multi-level Intrusion Detection System

Intrusion detection is a critical process in network security. Nowadays new intelligent techniques have been used to improve the intrusion detection process. This paper proposes a hybrid intelligent intrusion detection system to improve the detection rate for known and unknown attacks. We examined different neural network & decision tree techniques. The proposed model consists of multi-level based on hybrid neural network and decision tree. Each level is implemented with the technique which gave best experimental results. From our experimental results with different network data, our model achieves correct classification rate of 93.2%, average detection rate about 95.6%; 99.5% for known attacks and 87% for new unknown attacks, and 9.4% false alarm rate. Keywords-component; network intrusion detection; neural network; Decision Tree; NSL-KDD dataset