Deep Learning Models for Intrusion Detection Systems in MANETs: A Comparative Analysis
S. Saravanan, Showkat A. Dar, Aafaq Ahmad Rather, Danish Qayoom, Irfan Ali · Decision Making Advances · 2025
MANETs are dynamic, collaborative networks that maintain reliable connections in a self-organized manner. The intermediate nodes aim to forward the data packets between the source and destination nodes. However, most nodes are prone to attack, where intruders tend to attack these nodes and invade the data. With such consideration, the multipath routing in MANETs requires a serious intrusion detection system to detect the attacks in the network. In this paper, we develop a deep learning algorithm named graph neural network (GNN) to detect the possible intrusions of attacks in the nodes. GNN is trained with the possible datasets, and that is tested onto the network. The simulation shows a better resilience to the network against attacks than the other methods.