A Comparative Analysis of Machine Learning Models for Intrusion Detection in IoT Networks
Bildiriler > Tam Metin Bildiri
Yazarlar: Merve Candan, Ozgu Can
2025 5th International Conference on Electrical, Computer and Energy Technologies (ICECET), , , Uluslararası, Tam Metin Bildiri, ss 1-6
DOI: 10.1109/icecet63943.2025.11472081
Özet
The widespread adoption of Internet of Things (IoT) devices across various domains has significantly enhanced connectivity and automation. However, the inherent security vulnerabilities of these devices make them prime targets for cyberattacks. Ensuring the security of IoT ecosystems necessitates robust mechanisms for the detection and prevention of malicious activities. Intrusion Detection Systems (IDS) play a crucial role in this regard by ceaselessly tracking network traffic to identify anomalous behavior and potential threats. However, conventional IDS approaches often struggle to detect sophisticated and evolving attack patterns in IoT environments. Machine learning (ML) techniques have emerged as a promising solution for enhancing IDS capabilities by enabling adaptive and data-driven threat detection. This study conducts a comprehensive evaluation of various ML algorithms for IDS using the RT-IoT2022 dataset. Specifically, the performance of Random Forest, Decision Tree, K-Nearest Neighbors (KNN), Logistic Regression, Naive Bayes, and Gradient Boosting classifiers is assessed. These models are trained and tested, and their classification performance is evaluated using accuracy, precision, recall, and F1-score metrics. The experimental findings indicate that the Gradient Boosting algorithm outperforms other models, achieving the highest accuracy, precision, recall, and F1-score. While Random Forest and Decision Tree models also demonstrate strong classification performance, they exhibit higher computational costs in terms of processing time. The results of this study provide valuable insights for cybersecurity practitioners in selecting suitable ML-based IDS solutions for securing IoT networks. Furthermore, these findings serve as a foundation for future research aimed at optimizing IDS frameworks to enhance the resilience of IoT ecosystems against emerging cyber threats.