Efficient Deep Learning Method for Detection of Malware Attacks in Internet of Things Networks

In uncontrolled environments, the IoT devices are vulnerable to many attacks in network layer such as Malware Attack. The security of exchange data between the Internet of Things devices is very important. One of the most important areas of research is IoT centered on healthcare. The network of medical equipment and people is known as the “internet of medical things (IoMT)”. The sector will undergo a transformation as a result of improvements in the IoMT and less expensive technology implementation. The ability to monitor patients from a distance and administer care in an emergency will be more beneficial. In this paper, we propose a deep learning model for detecting Malware attacks in Network layer in medical IoT networks, which consists of 6 layers: An input layer of 2 nodes, 4 hidden layers of 4 nodes each one with a “ReLu” nonlinear activation function, and an output layer of 2 nodes with a “SoftMax” activation function. The model is trained to detect Malware attacks within 2 ms and can also be installed in IoT devices with small memory, enabling better protection of IoT networks and patient privacy information.