IoT DDoS Detection Based on Stream Learning
Gustavo Vitral Arbex, Kétly Gonçalves Machado, Michele Nogueira, Daniel Macêdo Batista, Roberto Hirata · 2021
The Internet of Things (IoT) represents a new reality, as smart devices spread quickly and a higher number of applications arises. This attracts the attention of not only legitimate users but also attackers aiming to jeopardize the entire IoT infrastructure. Intrusion detection mechanisms are paramount in this networking environment as its first line of defense. Hence, this work proposes a Network Intrusion Detection System (NIDS) that deals with the Distributed Denial of Service (DDoS) attack, one of the most critical attacks that occur through IoT. The proposed NIDS uses stream learning to detect DDoS attacks in the IoT network and is designed to be deployed in a fog infrastructure. The detection model, built on Hoeffding Anytime Tree (HATT) algorithm, achieved a 99% accuracy and a 99% recall.