XGB-RF: A Hybrid Machine Learning Approach for IoT Intrusion Detection

In the past few years, Internet of Things (IoT) devices have evolved faster and use these is exceedingly increasing to make our daily activities easier than ever. However, numerous security flaws persist on IoT due fact that majority them lack memory computing resources necessary for adequate operations. As a result, are affected by variety attacks. A single attack network systems or can lead significant damages in data privacy. machine-learning techniques be applied detect this paper, hybrid machine learning scheme called XGB-RF proposed detecting intrusion The method was N-BaIoT dataset containing hazardous botnet Random forest (RF) used feature selection eXtreme Gradient Boosting (XGB) classifier different types attacks environments. performance evaluated based several evaluation metrics demonstrates model successfully detects 99.94% After comparing it with state-of-the-art algorithms, has achieved better every metric. capable effectively, significantly contribute reducing concerns associated systems.