A Comprehensive Review of Intrusion Detection Systems for Routing Attacks in Mobile Ad Hoc Networks

Mobile Ad Hoc Networks (MANETs) are wireless networks that do not require any fixed infrastructure or central administration. The high vulnerability of MANETs to routing based security attack is mainly due to their dynamic topology, limited bandwidth, and distributed architecture, including black hole, wormhole, gray hole, rushing, and Sybil attacks. IDS (Intrusion Detection Systems) are crucial in detecting attacks and securing communications in MANETs. Machine Learning (ML) and Deep Learning (DL) methods have greatly enhanced the intrusion detection capability in recent years by allowing intelligent attack classification and anomaly detection. This review paper summarizes the existing IDS techniques for MANETs routing attack detection system. It presents the traditional IDS techniques, machine learning enabled IDS, and deep learning intrusion detection framework techniques. Existing research contributions are also tabulated and presented in a detailed comparative analysis based on the techniques used, attacks detected, datasets used, performance measures used, advantages and limitations. Moreover, the study identifies the significant research challenges and future directions for developing efficient, lightweight and intelligent IDS design for MANET security.