Securing smart cities through machine learning: A honeypot-driven approach to attack detection in Internet of Things ecosystems

Abstract

The rapid increase and adoption of Internet of Things (IoT) devices have introduced unprecedented conveniences into modern life. However, this growth has also ushered in a wave of cyberattacks targeting these often-vulnerable systems. Smart cities, relying on interconnected sensors, are particularly susceptible to attacks due to the expanded entry points created by these devices. A security breach in such systems can compromise personal data and disrupt entire ecosystems. Traditional security measures are inadequate against the evolving sophistication of cyberattacks. The authors aim to address these challenges by leveraging honeypot data and machine learning to enhance IoT security. The research focuses on three objectives: identifying datasets from IoT-targeted honeypots, evaluating machine learning algorithms for threat detection, and proposing comprehensive security solutions. Real-world cyber-attack datasets from diverse honeypots simulating IoT devices are analysed using various machine learning and neural network algorithms. Results demonstrate significant improvement in cyber-attack detection and mitigation when integrating honeypot data into IoT security frameworks. The authors advance knowledge and provides practical insights for implementing robust security measures in diverse IoT applications, filling a crucial research gap.