TRAFFIC SEASONALITY AWARE ADAPTIVE THRESHOLD ALGORITHM FOR DETECTION OF FLOODING BASED DENIAL-OF-SERVICE ATTACKS IN IoT NETWORKS

Abstract

The Internet of Things (IoT) is a new technology that connects and exchanges data with other devices and systems over the internet or other communication networks us- ing physical objects that are integrated with sensors, computing power, software, and other technology. The network nodes in a decentralised infrastructure are typically mobile and have limited resources, such as low memory, low processing power and inadequate battery backup. As a result, they are vulnerable to a variety of Denial- of-Service (DoS) attacks, of which SYN flooding, Route Request (RREQ) flooding and HELLO flooding are examples. It is crucial to identify these attacks to ensure that the network can survive an attack. However, most of the works that are now available employ fixed threshold algorithms which led to large false-positive rates. The majority of attacks vary seasonally and are challenging to detect with current techniques. This project suggests a technique for detecting flooding attacks that also consider network traffic seasonal changes.