An Enhanced Rule Approach for Network Intrusion Detection Using Efficient Data Adapted Decision Tree Algorithm

Data mining has been used extensively and broadly by several network organizations. Intrusion Detection is one of the high priorities & the challenging tasks for network administrators & security experts. Intrusion detection system is employed to protect the data integrity, confidentiality and system availability from attacks. IDS use the data mining techniques to analyze the resources from the database over a network. It is also necessary to develop a robust algorithm to generate effective rules for detecting the attacks. In this paper, Classification based optimization algorithms have been used to detect attacks over KDD CUP 99 dataset. Based on this dependency, an improved Efficient Data Adapted Decision Tree algorithm is proposed to overcome the drawbacks of the existing algorithm. The experimental results clearly show that the proposed EDADT algorithm achieved higher accuracy, less alarm rate & capable of detecting new type of attack efficiently.