Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{159744,
        author = {Anvika D Shriyan and Navya M R and Shrut Kriti and Khyati K Kaneria and Arun Vikas Singh},
        title = {Anomaly Detection in Cyber-Physical Systems in Fog Environment},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {9},
        number = {12},
        pages = {301-306},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=159744},
        abstract = {A cyber physical system(CPS) is an intelligent system which uses computer algorithms to monitor and control the functions of the system. Smart healthcare, smart electric grids, and aircraft autopilot systems are some examples of CPSs. Cyber Physical Systems have become highly integrated in the modern world. The importance of safeguarding these systems grows as this connection advances. Attacks against Cyber Physical Systems components can result in faulty sensing and actuation, catastrophic damage to physical items, and safety concerns. Anomaly detection can be used to detect and stop such attacks by monitoring system activity and classifying it as normal or anomalous. Machine learning algorithms have been proposed to build anomaly detection systems to hinder attacks on CPSs. However, the intricate interdependencies among numerous variables and a lack of labelled data in these systems render typical supervised machine learning methods ineffective. In this report, we propose an unsupervised anomaly detection method based on Generative Adversarial Networks (GANs), using Long-Short-Term-Memory Recurrent Neural Networks (LSTM-RNN) as the base models 

(namely, the generator and discriminator) in the GAN framework to capture the temporal dependencies of variables. Because intrusions must be stopped before the server is infected, anomaly detection in Cyber Physical Systems has strict latency constraints. Current anomaly detection models, despite having good detection rates, are excessively slow and unsuitable for latency-constrained situations. Hence, we plan to propose a model with lower latency, by using fog computing. Fog computing helps to bring computation power closer to end nodes, which helps to meet anomaly detection's low latency standards.
},
        keywords = {},
        month = {},
        }