• Shaik HafsaFarheen
• Bushra Tahseen

Mobile Ad hoc Networks (MANETs) play a crucial role in enabling flexible, infrastructure-less communication across diverse domains such as military operations, disaster recovery, and smart mobility. However, their highly dynamic topology, limited resources, and open wireless medium make them especially vulnerable to a wide range of security threats, including denial-of-service, blackhole, and wormhole attacks. Traditional intrusion detection systems often fail to cope with the scalability, adaptability, and evolving nature of adversarial behaviors in MANETs. To address these challenges, this research introduces an AI-Powered Intrusion Detection Framework designed to provide real-time threat identification with enhanced accuracy and reduced computational overhead. The proposed framework integrates machine learning and deep learning models to analyze traffic patterns, predict anomalies, and classify attack vectors, while adaptive feature selection minimizes resource consumption in constrained environments. Furthermore, a hybrid detection approach combining signature-based and anomaly-based techniques improves resilience against both known and zero-day attacks. Experimental validation on benchmark MANET datasets demonstrates significant improvements in detection rate, false positive reduction, and energy efficiency compared to conventional methods. This work provides a robust and intelligent security solution to safeguard MANETs, paving the way for secure, reliable, and scalable mobile networking.

Mobile Ad Hoc Networks, Intrusion Detection, Artificial Intelligence, Anomaly Detection, Machine Learning, Network Security.

"AI-Powered Intrusion Detection Framework for Mobile Ad Hoc Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 9, page no.d423-d429, September-2025, Available :http://www.jetir.org/papers/JETIR2509358.pdf

"AI-Powered Intrusion Detection Framework for Mobile Ad Hoc Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 9, page no. ppd423-d429, September-2025, Available at : http://www.jetir.org/papers/JETIR2509358.pdf