Recent Advances in Multi-Attack Detection using Forensics and Coherent Integrated Photonic Neural Networks-based Prevention for Secure IoT-MANETs: A Systematic Review

Abstract

The rapid expansion of Internet of Things (IoT) and Mobile Ad Hoc Networks (MANETs) has introduced significant security challenges due to their decentralized architecture, dynamic topology, and resource constraints. These networks are highly vulnerable to multi-attack scenarios, including denial-of-service (DoS), black hole, botnet, and data injection attacks. This paper presents a systematic review of recent advances in multi-attack detection using digital forensics and coherent integrated photonic neural networks for secure IoT-MANET environments. Artificial intelligence techniques, particularly machine learning and deep learning models, have shown remarkable capabilities in detecting and mitigating complex and evolving cyber threats. Recent studies indicate that AI-driven intrusion detection systems (IDS) can effectively classify malicious traffic and identify anomalies in real time.  Furthermore, photonic neural networks have emerged as a promising solution for high-speed, energy-efficient processing in large-scale IoT systems. Forensic-based frameworks enhance threat detection by analyzing network traffic patterns and digital evidence. Hybrid approaches combining deep learning with optimization techniques such as Particle Swarm Optimization (PSO) have demonstrated improved accuracy and reduced false alarm rates.  This review highlights recent developments, identifies key challenges, and outlines future research directions for designing robust, scalable, and intelligent multi-attack detection systems for secure IoT-MANETs.