Detecting Malicious IoT Traffic using Supervised Machine Learning Algorithms
Harikeish Fowdur, Sandhya Armoogum, Geerish Suddul, Vinaye Armoogum · 2022
IoT comprises of devices connected to each other through the internet. Such IoT networks are now becoming easy prey for attackers. The attacks conducted can however be detected through the use of machine learning techniques. In this paper, Random Forest, Logistic Regression, Naive Bayes and Decision Tree machine learning algorithms are investigated in order to detect malicious traffic in an IoT network. The IoT-23 dataset is used. Best results were obtained using Decision tree