A Layered Approach for Intrusion Detection Using Fuzzy Artmap Neural Network Classifier

Intrusion Detection Systems (IDS) is a key part of system defense, where it identifies abnormal activities happening in a computer system. In general, the traditional intrusion detection relies on the extensive knowledge of security experts, in particular, on their familiarity with the computer system to be protected. To reduce this dependence, various data-mining, soft-computing and machine learning techniques have been proposed in recent years for the development of better intrusion detection systems. Many researchers used Conditional Random Fields and Layered Approach for purpose of intrusion detection. They also demonstrated that high attack detection accuracy can be achieved by using Conditional Random Fields and high efficiency by implementing the Layered approach. In the paper we propose a new method called fuzzy ARTMAP classifier (FAM) and clustering technique for effectively identifying the intrusion activities within a network. Processing huge data would make the system error prone, hence clustering the data into groups and then processing will result in having a better system. From each of the cluster, representative data is selected in the selective process for further processing. For classification process, layered fuzzy ARTMAP will have the better results when compared to other normal classifier algorithms.