Developing an Intrusion Detection System Based on Fuzzy Clustering and Whale Optimization Algorithm

Nowadays, computer networks are being widely used in the world. Due to the widespread use of the internet, computer systems are prone to information theft and this has led to the emergence of intrusion detection systems (IDS). Thus, network security has become an essential subject in computer science responding to the increase of sensitive information. The current research has used fuzzy C-means (FCM) and Whale optimization algorithm (WOA) to propose an unsupervised machine learning intrusion identification system and has tested it with the KDD Cup 99 standard intrusion detection dataset. In this method, fuzzy C-means has been applied in order to distinguish intrusive activities from normal activities and Whale optimization algorithm has been used to achieve optimal separations among these activities. In order to help FCM, the WOA has been applied to start with suitable cluster centers rather than randomly initialized centers. Experimental results on KDD Cup 99 dataset showed that the proposed method offers higher detection accuracy and a lower false alarm rate compared to other similar algorithms. Therefore, the findings of the present study would be effective in solving complex problems related to IDS.