Identificação de ataques de negação de serviço distribuído na computação em névoa utilizando um sistema de inferência fuzzy

Abstract

The constant use of Internet of Things (IoT) devices raises concern about cybersecurity due to limited resource of these devices. Fog Computing, an intermediate layer between cloud and IoT, has several known vulnerabilities, which can be exploited by threats such as the Distributed Denial of Service (DdoS) attack. MQTT (Message Queue Telemetry Transport) is the most widely used protocol between fog computing and IoT. In the fog computing, an MQTT broker is the equipment responsible for managing communications originating from IoT devices, being one of the most targeted device in DdoS attacks. This attack, when depleting the broker’s physical resources, can cause different levels of problems ranging from a small delay in communications, to a complete interruption of service. This work proposes a Fuzzy Inference System (FIS) capable of detecting, identifying and infer the degree of membership of a DdoS attack in a fog node by analyzing its energy consumption pattern.