Denial of Service Mitigation in Wireless Body Area Network Using Deep Learning

With increasing use of Wireless Body Area Networks (WBANs), there has been an increase in the number of cybersecurity risks that have the potential to harm the network. Because of the increasing number of attacks in WBAN, the inefficiency of the communication service and the increased latency influence the entire network. This is because of the interconnected nature of the network. An attack that is known as a denial-of-service attack is a form of attack that is particularly prevalent on networks such as these. Throughout the course of this work, we construct an intrusion prevention system that leads to a significant reduction in the number of denial-of-service attacks that take place in WBAN. Additionally, the system makes use of the Dense Neural Network (DenseNet) method, which obtains its training data from several different datasets, to validate attacks in WBAN. Through the utilization of the database of distributed denial of service attacks as a test, the trained model can identify attacks. The ability of DenseNet to significantly improve the detection and prevention rates in the simulation is one of the ways in which it displays its value in comparison to other deep learning models.