Next-Gen Threat Detection: Leveraging AI and Cyber Twin Technologies for IoT Security
R. Leela Jyothi, R Jagadeesha · 2024
The rapid proliferation of the Internet of Things (IoT) has led to a surge in cyber threats, demanding the development of robust security frameworks. This paper introduces an advanced threat detection model, leveraging Artificial Intelligence (AI) and Cyber Twin Technologies for enhanced IoT security. The proposed framework integrates a Cyber Twin-a digital replica of physical IoT devices-with real-time data analytics to detect, predict, and respond to sophisticated cyber-attacks. The Cyber Twin continuously monitors IoT networks, identifying abnormal behaviors and enabling the implementation of dynamic security measures through AI-driven intrusion detection systems (IDS). A hybrid deep learning approach combining Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) is utilized to enhance anomaly detection and threat classification accuracy. The system’s ability to simulate various attack scenarios within a digital environment facilitates the development of effective countermeasures while minimizing the impact on actual IoT operations. Experimental results demonstrate significant improvements in detection accuracy, reduced false positives, and enhanced system resilience. The proposed AI and Cyber Twin-based threat detection model sets a new benchmark in safeguarding IoT infrastructures against emerging cyber threats. Experimental results show a detection accuracy of 96.2%, a 35% reduction in response time, and a 15% reduction in false positives compared to traditional rule-based methods. Additionally, the system demonstrated 98.1% resilience against simulated attacks, setting a new benchmark in safeguarding IoT infrastructures against emerging cyber threats.