Advanced Intrusion Detection in MANETs: A Survey of Machine Learning and Optimization Techniques for Mitigating Black/Gray Hole Attacks

Abstract

Mobile Ad Hoc Networks (MANETs) are dynamic networks without fixed infrastructure, making them particularly vulnerable to security threats such as black and gray hole attacks. As these attacks grow more sophisticated, advancing detection methods become critical. This survey critically evaluates existing detection techniques and identifies major gaps in current research. It focuses on a comprehensive classification and in-depth analysis of attack detection methods, particularly those employing advanced Machine Learning techniques. We adopt a structured approach, analyzing MANET characteristics and detailing black and gray hole attacks. The evaluation covers various detection and mitigation techniques, with a strong emphasis on the innovative use of ML and optimization methods like Federated Learning (FL), reinforcement learning, and metaheuristic algorithms. Our findings indicate that advanced ML techniques, especially Long Short-Term Memory (LSTM) networks and FL, significantly enhance detection accuracy and robustness against these attacks. We also discussed the potential of game theory and reinforcement learning for optimizing routing protocols and improving network resilience. The survey underscores the necessity for ongoing research into more sophisticated and adaptable detection mechanisms, urging both academic and practical communities to explore novel approaches for developing more secure, efficient MANET systems.

Keywords

• Mobile ad hoc networks (MANETs)
• blackhole attacks
• gray hole attacks machine learning in network security
• federated learning (FL)
• optimization techniques in security