Copyright © 2026 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{175716,
        author = {Maimoon Shirin M},
        title = {Enhanced Intrusion Detection in Cyber Physical Systems using Graph Neural Network},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {3593-3598},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175716},
        abstract = {A computer network may be impacted by hostile attacks, malicious software, and computer viruses. As a part of a defense technology, intrusion detection plays a major role in protecting the networks and its data. Poor accuracy, inadequate detection, a high false-positive rate, and an inability to handle novel incursion types are some of the problems that plague traditional intrusion detection systems. We suggest a unique deep learning-based technique to identify cybersecurity flaws and breaches in cyber-physical systems in order to address these problems. The suggested framework compares deep learning-based discriminative methods with unsupervised methods. This paper presents a promising solution such as Graph Neural Network (GNN) to detect network attacks in IoT-driven IICs networks. The results shows an 95% in terms of accuracy, reliability, recall, and efficiency in identifying intrusion attacks. For this paper, the output achieves the maximum accuracy rate in KDCupp99 datasets.},
        keywords = {Intrusion Detection, Graph Neural Network, Cyber Physical System, Cyberattacks, Malicious, Normal attack.},
        month = {April},
        }