In the era of the Internet of Things (IoT), an increase in IoT devices due to its internet connectivity leads to more attractive data for cybercriminals to cause attacks. Attacks in IoT seek to gather access to IoT devices to cause harm to the devices, which then leads to impact the system’s security and privacy. Distributed Denial-of-Service (DDoS) attacks in IoT networks are one of the challenging attacks and utilize the limited resources in IoT devices. A DDoS attack is a spiteful attempt to interrupt the normal traffic of a targeted network by staggering the target or its surrounding infrastructure with a massive amount of Internet traffic.
The main significance of DDoS is storage limitation and network capacity that cause an attack in IoT applications. DDoS utilizes multiple agents to generate attacks to damage the IoT network. Deep learning models are highly effective for detecting DDoS attacks in IoT networks due to their high-level feature representations of the traffic from low-level. The advantages of deep learning models in DDoS attack detection are automatic feature engineering and high performance. Random forest (RF), recurrent neural network (RNN), Convolutional Neural Network (CNN), multilayer perceptron methods, long short term memory (LSTM), and their combinations are some of the deep learning models used for DDoS attack detection.