An intelligent hybrid approach combining fuzzy C-means and the sperm whale algorithm for cyber attack detection in IoT networks.

The Internet of Things (IoTs) has revolutionized cities, enabling them to become smarter. IoTs play an important role in monitoring the traffic cameras, roads, smart farming, connected vehicles, air quality, water level, humidity, and carbon dioxide pollution levels in city buildings. One of the major challenges of smart cities is the cyber threat to sensitive data. This paper presents an intelligent approach for detecting cyberattacks and mitigating malicious events in IoT-based smart systems. The proposed approach, known as FCM-SWA, hybridizes a fuzzy C-mean (FCM) with a sperm whale algorithm (SWA). In the first step, we use a novel SWA optimization algorithm to enhance the FCM performance and provide effective defenses against various types of smart city attacks. Next, we propose an adaptive threshold strategy to enhance the global search capability of SWA and prevent the algorithm from settling into local optima. Lastly, we present an efficient scaling approach that solves the clustering problem and finds the optimal cluster center, striking a balance between exploration and exploration in the search space. The proposed FCM-SWA model does better than related and state-of-the-art methods in terms of accuracy, detection rate, precision rate, and F1-scores, as shown by experiments on the NSL-KDD, AWID, and BoT-IoT datasets.