Towards a conceptual framework for AI-driven anomaly detection in smart city IoT networks for enhanced cybersecurity

Abstract

As smart cities advance, Internet of Things (IoT) devices present cybersecurity challenges that call for innovative solutions. This paper presents a conceptual model for using AI-enabled anomaly detection systems to identify anomalies and security threats in smart city IoT networks. The foundation is supported by the Complex Adaptive Systems (CAS) theory, Technology Acceptance Model (TAM), and Theory of Planned Behavior (TPB). In this framework, the importance of user engagement in ensuring effective AI-driven cybersecurity solutions is underlined with an emphasis on technological readiness and human interaction with AI. By fostering a security-conscious culture through continuous education and skills development, this research provides actionable insights for enhancing the resilience of smart cities against evolving cyber threats. The proposed framework lays the groundwork for future empirical studies and offers practical guidance for policymakers and urban planners dedicated to safeguarding the digital infrastructures of potentially tomorrow's cities – the smart cities.