6G-Enabled Attack Detection System for IoT-Driven Smart City Using Machine Learning

Rapid urbanization has led to the emergence of smart cities, where interconnected devices and technologies aim to improve urban management. A smart city utilizes Internet of Things (IoT) sensors in urban environments to collect data and automate the systems. However, the exponential growth of IoT devices presents significant challenges, including inadequate security high latency, and limited bandwidth. The advent of sixth-generation (6G) wireless communication technology, marks a paradigm shift in addressing these challenges. In this study, a 6G-enabled Attack Detection System (6G-IoTSCADS) for IoT-driven smart cities is introduced. The proposed system utilizes the feature ranking and selection method to obtain an optimized feature set, which is then fed into the attack detection model i.e. eXtreme Gradient Boosting (XGBoost). The proposed system is evaluated using an AIoT-SOL IoT-based dataset. The results demonstrate the superiority of the proposed system over other machine-learning techniques.