Anomaly and Malware Detection in IoT Networks
Qusai Hasan, Sahar Abdelbasit, Kevser Ovaz Akpinar · 2025
The rapid expansion of the Internet of Things (IoT) has led to significant security challenges, with over 30% of attacks targeting IoT devices on mobile networks. This paper emphasizes the necessity for secure, adaptable, and programmable network services to ensure user privacy and quality of service. To address these security concerns, the study explores the effectiveness of machine learning algorithms in detecting anomalies within IoT network data. Utilizing the IoT-23 dataset, which comprises both malicious and benign traffic from various IoT devices, the research compares multiple machine learning techniques, including Decision Tree (DT), Support Vector Machine (SVM), and Perceptron. The findings reveal that the DT algorithm outperforms the others, achieving an impressive accuracy rate of 99.8% in identifying malicious traffic. This highlights the potential of machine learning in enhancing security measures within the IoT ecosystem, paving the way for future research in this critical area of cybersecurity