Detection of DIS Flooding Attacks in IoT Networks Using Machine Learning Methods

In today, Internet of Things (IoT) has a wide usage area and makes easier our lives with smart objects that can communicate each other without human intervention. However, as Wireless Sensor Networks, IoT networks bring new risks. These risks reaching worrying levels cause some significant issues such security, privacy, energy in the network topology. The IPv6 Routing Protocol for Low-Power Lossy Network (RPL) is routing protocol resource-constrained devices networks. When it transmits packets between nodes, nodes be exposed to series attacks. DODAG Information Solicitation (DIS) Flooding attack one most effective types attacks against this negatively affects level node its limited processing capacities. Although many intrusion detection methods are used detect innovative energy-saving needed. DIS prevention have not been adequately presented literature. To address mentioned need, study provides high-performance by applying Logical Regression (LR) Support Vector Machine machine learning methods. experiments implemented using Contiki-Cooja simulation environment experimental results evaluated various performance metrics. It concluded LR achieves higher terms accuracy.