Towards finding Hybrid Machine Learning Models for detection of IoT Botnets

The rapid expansion of Internet of Things (IoT) devices has significantly increased their vulnerability to cyber-attacks, with IoT botnets posing a critical threat by enabling distributed denial-of-service (DDoS) attacks, data exfiltration, and other malicious activities. Traditional security measures often fall short of effectively mitigating these threats due to the resource limitations of IoT devices. This research explores the use of machine learning (ML) models for IoT botnet detection, focusing on Support Vector Machine (SVM), Random Forest (RF), and Decision Tree (DT) techniques. Furthermore, two hybrid models are proposed: Isolation Forest (IF) combined with SVM for anomaly detection and classification, and K-Means clustering integrated with Random Forest to enhance detection accuracy. These models are evaluated based on key performance metrics, including accuracy, precision, recall, and F1 score, to identify their effectiveness in detecting IoT botnets. The study demonstrates the potential of ML-based approaches, particularly hybrid models, to strengthen IoT security and overcome the limitations of traditional methods in resource-constrained environments.