article · World Journal of Advanced Engineering Technology and Sciences
Optical fibre communication networks carry vast amounts of data across digital infrastructure, making them critical targets for cyberattacks. Protecting these high-speed systems demands automated and adaptive security measures capable of identifying threats in real time. Machine learning algorithms, including Support Vector Machines, Random Forests, Deep Neural Networks, and Autoencoders, offer mechanisms to detect network disruptions, anomalous traffic, and malicious intrusions. Combining deep learning with statistical signal processing creates hybrid frameworks that improve detection accuracy while minimising false alarms. Deploying these methods across large-scale networks introduces practical challenges relating to system latency, computational scalability, and model interpretability. Addressing these operational demands involves exploring edge computing and federated learning for decentralised monitoring, alongside explainable artificial intelligence, graph-based detection, and transfer learning to build resilient, autonomous, and self-healing optical communication environments.
Optical fibre cables form the backbone of modern digital infrastructure, transmitting huge volumes of global communications. As networks grow faster and more intricate, cyberattacks become harder to detect using traditional methods. Developing intelligent systems that spot disruptions instantly without interrupting operations helps prevent widespread network outages and protects essential communication services from evolving digital threats.
This work outlines concepts that could assist telecommunications providers, network operators, and infrastructure security teams in building automated defence tools for optical communication systems. Because the work is a review synthesising existing algorithms, datasets, and emerging trends rather than presenting a tested operational product, the underlying technology remains in the early stages of research and development before being viable for commercial deployment in live networks.
AI-generated from the published abstract. Always read the original work before citing.
The increasing complexity and data throughput of optical fiber communication systems have made them critical yet vulnerable components of modern digital infrastructure. With the rapid growth of high-speed networks, ensuring cybersecurity in these systems requires intelligent, adaptive, and real-time mitigation strategies. This review examines the application of machine learning (ML)-enabled anomaly detection models for identifying and mitigating cyberattacks in optical fiber communication environments. It highlights how supervised, unsupervised, and reinforcement learning algorithms—such as Support Vector Machines (SVM), Random Forests, Deep Neural Networks (DNN), and Autoencoders—enable real-time detection of network anomalies, signal disruptions, and malicious intrusions. Furthermore, the paper explores the integration of hybrid ML frameworks combining statistical signal processing with deep learning for enhanced detection accuracy and low false alarm rates. Special emphasis is placed on the challenges of model interpretability, scalability, and latency in large-scale fiber networks, alongside the role of edge computing and federated learning in decentralized security monitoring. The study also evaluates emerging trends such as graph-based anomaly detection, explainable AI (XAI), and transfer learning approaches for resilient optical network protection. By synthesizing current methodologies, datasets, and performance metrics, this review provides a comprehensive perspective on the state-of-the-art in ML-driven anomaly detection and outlines research directions for achieving secure, autonomous, and self-healing optical communication systems.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.30574/wjaets.2025.17.2.1454
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
