IoT Ddos Attack Detection Using Machine Learning

Abstract

The distribution strategy of a botnet mainly directs its configuration, installing a support of bots for coming exploitation. In this article, we utilize the sources of pandemic modeling to IoT networks consisting of WSNs. We build a proposed framework to detect and abnormal defense activities. According to the impact of IoT-specific features like insufficient processing power, power limitations, and node density on the formation of a botnet, there are significant challenges. We use standard datasets for active two famous attacks, such as Mirai. We also used many machine learning and data mining algorithms such as LSVM, Neural Network, and Decision tree to detect abnormal activities such as DDOS features. In the experimental results, we found that the merge between random forest and decision tree achieved high accuracy to detect attacks.