Artificial Intelligence Techniques for Multi-Attack Detection using Forensics and Coherent Integrated Photonic Neural Networks-based Prevention for Secure IoT-MANETs: Trends and Challenges

Abstract

The rapid growth of Internet of Things (IoT) and Mobile Ad Hoc Networks (MANETs) has significantly increased the complexity and vulnerability of modern communication systems. Due to their decentralized architecture, dynamic topology, and limited resources, IoT-MANET networks are highly susceptible to multiple simultaneous cyber-attacks such as denial-of-service (DoS), black hole, wormhole, and botnet attacks. This paper presents a comprehensive review of artificial intelligence (AI) techniques for multi-attack detection using forensic analysis and coherent integrated photonic neural networks for secure IoT-MANET environments. Deep learning-based intrusion detection systems (IDS), including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and hybrid architectures, have demonstrated superior performance in identifying complex attack patterns. Studies show that deep learning models can achieve detection accuracy exceeding 98% in multi-attack scenarios. Digital forensics enhances detection by analyzing network logs and correlating evidence across distributed nodes, enabling identification of coordinated attacks. Additionally, photonic neural networks provide high-speed and energy-efficient processing, making them suitable for large-scale IoT environments. Hybrid approaches combining AI with optimization techniques further improve detection accuracy and reduce false alarm rates. This review highlights recent trends, challenges, and future directions for developing intelligent, scalable, and secure IoT-MANET systems.