Attribute Reduction and Design of Intrusion Detection System Based on K-Nearest Neighbours

Intrusion detection is a necessary step to identify unusual access or attacks to secure internal networks. Nowadays, challenged by malicious use of network and intentional attacks on personal computer system, intrusion detection system (IDS) has become a useful infrastructural mechanism for securing critical resource and information. Most current intrusion detection systems focus on hybrid machine learning technologies. The related work has demonstrated that they can get superior performance than applying single machine learning algorithm in detection model. Besides, in the related works, feature selecting and representing techniques are also essential for achieve high efficiency and effectiveness. Performance of specified attack type detection should also be improved and evaluated. In this technique inclusion of classification for selecting most relevant attributes and use of k-Nearest Neighbours (K-NN) to detect attacks. Our system can achieve good accuracy, detection rate and false alarm rate using K-NN.