This is the authors' abstract. We don't add key points for this paper.
Mobile Ad Hoc Networks (MANETs) are decentralized and self-configuring networks that facilitate communication without fixed infrastructure. However, their open and dynamic nature makes them highly vulnerable to various security threats, particularly malware attacks. Traditional signature-based malware detection systems are ineffective in such environments due to their inability to detect novel and evolving threats. This paper explores the advancements in machine learning (ML) techniques for dynamic malware detection in MANETs. We analyze various ML-based approaches, including supervised, unsupervised, and deep learning models, that enhance the accuracy and efficiency of threat detection. Furthermore, we discuss feature selection techniques, behavioral analysis, and anomaly detection methods that improve malware identification in real time. The integration of AI-driven malware detection solutions in MANETs significantly enhances their resilience against sophisticated attacks. The study concludes by highlighting the challenges and future research directions in developing adaptive and intelligent malware detection systems for secure mobile communication.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Sharma et al. (2024) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: