Applying Machine Learning Techniques for Early Detection of Cyber Attacks on IoT Devices

Authors

Noor Adnan Allamy, Researcher, Islamic Azad University, Islamic Republic of IranFollow

Article Type

Article

Abstract

This research designs, implements, and evaluates a machine learning-based framework for the early detection of cyber attacks targeting Internet of Things (IoT) devices, with a specific focus on the context and challenges present in Iraq. The study conducts a comparative analysis of three supervised learning algorithms—Support Vector Machine (SVM), Random Forest (RF), and Deep Neural Networks (DNN)—using a combination of benchmark datasets (NSL-KDD, CIC-IDS-2017, Bot-IoT) and a synthesized dataset adapted to simulate the Iraqi threat landscape. Key performance metrics, including accuracy, precision, recall, and F1-score, were used for evaluation. The proposed Random Forest model demonstrated superior performance, achieving an accuracy of 99.54% in detecting a range of attacks, including DDoS and data exfiltration, outperforming baseline models by a significant margin. The results confirm that machine learning offers a viable and highly effective solution for enhancing IoT security. This study’s primary contribution lies in developing and validating a tailored cybersecurity strategy that addresses the specific needs of Iraq’s burgeoning digital infrastructure, particularly within its critical sectors such as energy and finance, thereby providing a practical pathway toward greater national cyber resilience.

Keywords

Internet of things (IoT), Cybersecurity, Machine learning, Intrusion detection system (IDS), Support vector machine (SVM), Random forest, Deep learning, Iraq, Critical infrastructure protection

Recommended Citation

Allamy, Noor Adnan (2025) "Applying Machine Learning Techniques for Early Detection of Cyber Attacks on IoT Devices," Al-Esraa University College Journal for Engineering Sciences: Vol. 7: Iss. 12, Article 5.
DOI: https://doi.org/10.70080/2790-7732.1075