Enhancing Smart City Security: An Intrusion Detection System Using Machine Learning Methods With the UNB CIC IoT 2023 Dataset

Abstract

Smart cities, characterised by their extensive use of IoT devices, aim to enhance urban living through improved efficiency, sustainability and quality of life. However, the widespread integration of IoT technology introduces significant cybersecurity challenges, including vulnerabilities to cyberattacks, data breaches and infrastructure resilience issues. Addressing these challenges is critical to realising the full potential of smart city initiatives. Intrusion detection systems (IDS) play a vital role in safeguarding smart city environments. Numerous studies have explored various IDS methodologies, yet the dynamic and complex nature of smart city IoT networks demands continuous advancements. In this article, we present a novel IDS approach that leverages machine learning techniques to enhance the detection and prevention of cyber threats in smart cities. Utilising the UNB CIC IoT 2023 Dataset, we develop and evaluate multiple models, including Random Forest Classifier, Decision Tree Classifier, KNN and AdaBoost. Our proposed IDS framework emphasises real-time threat detection ensuring both low latency and high accuracy. Through comprehensive data preprocessing and rigorous model training, our system demonstrates exceptional performance in identifying and neutralising cyber threats. The findings from this research reveal significant improvements in the security and privacy of smart city IoT infrastructures highlighting the effectiveness of integrating advanced AI methodologies.