In the wireless network, the MANET is a core technology that offers multi-hop communications between the source node (SN) and destination node (DN). The MANETs are susceptible to diverse security attacks due to the broadcast behaviour of transmission, restricted computation ability, and increasing application areas. Thus, intrusion detection is needed to handle these security issues. This work develops an efficient intrusion detection system (IDS) in MANET utilizing MLVQ neural network (NN). The proposed system offers energy-efficient data transmission (DT) by sending data via the optimal path. Then, the MLVQ NN detects the attacked data and normal data in the intrusion detection phase. The data are isolated and stored in a log file. Later, the optimal path is chosen by BM-MSOA centered on the MN residual energy and path distance. The proposed methodology detects intrusion with higher accuracy and minimal energy consumption (EC) compared with prevailing techniques. © 2025 Elsevier B.V., All rights reserved.