A Comprehensive Review of Multi-Attack Detection using Forensics and Coherent Integrated Photonic Neural Networks-based Prevention for Secure IoT-MANETs

Abstract

The rapid growth of Internet of Things (IoT) and Mobile Ad Hoc Networks (MANETs) has introduced significant security challenges due to their decentralized and dynamic nature. These networks are highly vulnerable to multi-vector attacks such as Distributed Denial of Service (DDoS), black hole, wormhole, and botnet attacks. Traditional intrusion detection systems often fail to detect complex and evolving threats in real time. Recent advancements in artificial intelligence, network forensics, and photonic neural networks have emerged as promising solutions for multi-attack detection and prevention. Forensic-based investigation techniques enable detailed analysis of network traffic patterns and attack behaviours, enhancing detection accuracy. Machine learning and deep learning models have demonstrated high efficiency in identifying multi-vector cyberattacks through traffic feature analysis and classification. Furthermore, photonic neural networks provide ultra-fast data processing capabilities, making them suitable for high-speed IoT environments. Graph-based and multi-stage intrusion detection systems further improve detection of complex attacks by analyzing relationships between nodes and attack evolution patterns. Hybrid optimization approaches combining AI and forensic techniques enhance detection performance and reduce false positives. This review presents recent advances in multi-attack detection using forensic analysis and photonic neural networks in IoT-MANET environments. It highlights key techniques, comparative insights, challenges, and future research directions toward secure and intelligent network systems.

IoT Security, MANET, Multi-Attack Detection, Network Forensics, Photonic Neural Networks, Intrusion Detection System, Deep Learning.