A HYBRID FRAMEWORK BASED ON NEURAL NETWORK MLP AND K-MEANS CLUSTERING FOR INTRUSION DETECTION SYSTEM

Due to the widespread use of Internet and communication networks, in case a reliable and secure network plays a crucial role for information technology (IT) service providers and users. The hardness of network attacks, as well as their complexity, has also increased lately. High false alarm rate is a big issue for majority of researches in this area. To overwhelm this challenge a hybrid learning approach is proposed, employing the combination of K-means clustering and Neural Network Multi-Layer Perceptron (MLP) classification. Concerning the robustness of K-means method and MLP algorithms benefits, this research is the part of an effort to develop a hybrid information detection system (IDS) which is able to detect high percentage of novel attacks while keep the false alarm at low rate. This paper provides the conceptual view and a general framework of the proposed system.