An Intrusion Detection System for MANET using CRF Based Feature Selection and Temporal Association Rules

摘要

As the Internet services spread all over the world, many kinds of security threats are introduced by malicious users. For the secured usage of the internet, the intrusion detection system plays a main role. Intrusion is an unauthorized access of the network resource by either a person or any software program. The role of the IDS is to analyze the network traffic and gives alerts about the attacks. In this study, researchers propose a new intrusion detection system using the temporal association rules for effective classification. Moreover, a new feature selection algorithm based on the Conditional Random Field (CRF) is used to improve the detection accuracy. The experimental results of the proposed model show that this system detects anomalies with low false alarm rate and high detection rate when tested with KDD Cup'99 dataset.