Building a Fuzzy Classifier Based on Whale Optimization Algorithm to Detect Network Intrusions

The quantity of network attacks and the harm from them is constantly increasing, so detection these an urgent task in information security field. In this paper, we investigate approach to building intrusion systems using a classifier based on fuzzy rules. process creating given set input output data can be presented as solution problems clustering, informative features selection, parameters rule antecedents optimization. To solve problems, whale optimization algorithm used. performance algorithms for constructing metaheuristic estimated KDD Cup 1999 dataset. On average, resulting classifiers have type I error 0.92% II 1.07%. obtained results are also compared with other classifiers. comparison shows competitiveness proposed method.