Detecting Destructive Nodes with the Aim of Reducing Black Hole Attack Using Response Time Based on Machine Learning Model in Mobile Case Networks

Mobile case networks, self-configurable, self-organized networks of mobile nodes that can move freely and independently in any direction without any restrictions, and use wireless links to communicate without relying on any specific, pre-designed infrastructure. These networks are widely used in applications such as military and disaster relief. However, due to their dynamism, lack of infrastructure, and lack of certificate authorization, they are vulnerable to a variety of attacks and security threats. One solution to provide security in these networks is to deploy intrusion detection systems (IDS). Black hole attacks are among the most common attacks in mobile case networks, which are discussed in this article in order to detect and isolate the black hole attack, a four-phase approach is proposed, in the first phase, clustering is done using the k-nearest neighbor algorithm (KNN), in the second phase, using the beta distribution, the confidence of each node and its remaining energy is calculated. Then, in the third phase, the cluster node is selected using fuzzy inference and finally, in the fourth phase, the response time is calculated based on the deep learning model. The simulation results show that the proposed approach provides better results with less routing overhead calculations and has improved parameters such as packet loss rate, operational throughput, packet delivery ratio, total network latency, and normal routing load compared to other methods.