Recent Advances in Similarity-Navigated Graph Neural Networks and Lightweight Cryptography for Preventing Black Hole Attacks in MANET: A Systematic Review

Abstract

Mobile Ad Hoc Networks (MANETs) are highly dynamic and infrastructure-less networks that are vulnerable to various routing attacks, particularly black hole attacks, where malicious nodes absorb and drop packets. Recent advancements in artificial intelligence and cryptographic techniques have significantly improved the detection and prevention of such attacks. This systematic review focuses on the integration of similarity-navigated Graph Neural Networks (GNNs) and lightweight cryptographic mechanisms to enhance security in MANET environments. GNNs enable efficient representation of network topology and node relationships, allowing detection of anomalous behavior based on similarity measures and structural patterns. Concurrently, lightweight cryptography ensures secure communication with minimal computational overhead, making it suitable for resource-constrained MANET devices. The review covers studies, analyzing methodologies such as trust-based routing, deep learning-based intrusion detection, federated learning, and blockchain-assisted security frameworks. The findings indicate that hybrid approaches combining GNN-based anomaly detection with lightweight encryption significantly improve detection accuracy, packet delivery ratio, and network resilience. However, challenges such as scalability, energy efficiency, and real-time adaptability remain. This paper provides a comparative analysis and highlights future research directions for secure MANET architectures.