Detecting IoT Network Breach Using the Random Forest Classifier
K. Sasikala, S. Vasuhi · 2024
Intrusion detection faces particular issues due to the interconnection and resource constraints of Internet of Things (IoT) devices. A complete collection of network traffic statistics pertaining to IoT security situations may be found in the CIC-IDS 2018 dataset. In this work, the Random Forest classifier, a flexible machine learning technique renowned for its high accuracy in handling heterogeneous data is used to address the critical problem of IoT network security. The intrusion detection system is developed using features taken from the CIC-IDS 2018 dataset, and it achieves an astounding accuracy rate of 99.96%.This remarkable outcome shows how well the Random Forest classifier works to identify and classify different types of network intrusions, including those that affect Internet of Things devices. The study enhances the security stance of Internet of Things networks by offering valuable perspectives on the application of machine learning methods for dependable intrusion detection in IoT environments.