A novel fuzzy anomaly detection algorithm based on artificial immune system

More and more intrusion detection systems were developed, but most of these systems have very poor accuracy. To overcome this problem, a self-adaptive anomaly detection system was developed using fuzzy detection anomaly algorithm with negative selection of biology. The algorithm improves the accuracy of the detection method and produces a novel method to measure the deviation from the normal that does not need a discrete division of the non-self space. The proposed anomaly detection model is designed as flexible, extendible, and adaptable in order to meet the needs and preferences of network administrators and can be also supplied for IPv6 environment. Different experiments are performed with MIT-DARAP 1999 dataset (Lippmann et al., 2000) and real word data from different sources. The experimental results show that the proposed algorithms provide some advantages over other algorithms