A Survey Paper based: Network Anomaly Detection for IoT Systems in Smart City using Machine Learning Approach

The rapid development of smart city infrastructures relies heavily on the seamless integration of Internet of Things (IoT) systems to enhance urban management and services. However, this interconnectedness also presents significant security challenges, particularly with network anomalies that can disrupt operations and compromise data integrity. The framework is designed to handle the complexity and scale of smart city environments, ensuring real-time response and high detection accuracy. Through a comprehensive analysis and case studies, we demonstrate the efficacy of the proposed model in minimizing false positives and enhancing threat detection. Our findings highlight the importance of adaptive and scalable solutions that align with the evolving nature of IoT-based smart cities. This work contributes to developing more secure and resilient urban systems by providing an effective strategy for detecting and mitigating network anomalies.