An Enhanced Machine Learning Model for Real-Time Anomaly Detection in Cyber-Physical Systems

Karen Robinson; Nancy Allen; Christopher Young

doi:10.62951/ijies.v1i3.67

Authors

Karen Robinson University of Cambridge, Inggris
Nancy Allen University of Cambridge, Inggris
Christopher Young University of Cambridge, Inggris

DOI:

https://doi.org/10.62951/ijies.v1i3.67

Keywords:

Cyber-Physical Systems, Anomaly Detection, Machine Learning, Real-Time Monitoring, Convolutional Neural Networks

Abstract

As cyber-physical systems (CPS) gain prevalence in sectors such as manufacturing, transportation, and critical infrastructure, ensuring their security and reliability is paramount. Traditional anomaly detection methods often fall short due to the dynamic and complex nature of CPS, leading to missed or false alarms. This study introduces an enhanced machine learning model that integrates statistical and deep learning techniques for real-time anomaly detection in CPS. By employing a hybrid approach of convolutional neural networks (CNNs) with statistical pattern recognition, the model demonstrates improved detection accuracy and responsiveness. Performance is evaluated using industry-standard CPS datasets, showing that the proposed model outperforms existing techniques in both accuracy and efficiency.

References

Zhang, Y., Lee, J., & Brown, T. (2021). "Real-Time Anomaly Detection in Industrial Cyber-Physical Systems." Journal of Industrial Applications, 33(4), 105-115.

Jiang, R., & Xu, F. (2022). "Machine Learning for Anomaly Detection in Smart Factories." IEEE Transactions on Industrial Informatics, 12(1), 44-58.

Lee, S., & Kim, J. (2020). "Advanced Techniques for Cyber-Physical Security." Journal of Information Security, 28(3), 220-231.

He, Q., & Wang, L. (2022). "Deep Learning in Cyber-Physical Systems: Applications and Challenges." Computers and Security, 37(2), 210-229.

Xu, X., Li, Y., & Feng, Z. (2021). "Evaluating Statistical Models for Anomaly Detection in CPS." Journal of Cybersecurity Research, 14(5), 317-328.

Goh, J., Adepu, S., & Teo, H. (2021). "The SWaT Dataset: Benchmarking CPS Anomaly Detection Models." Cybersecurity Advances, 18(1), 40-52.

Taormina, R., Galelli, S., & Noto, L. (2021). "Benchmarking Water Security Using BATADAL." Water Systems Journal, 23(4), 223-240.

Li, H., & Huang, M. (2020). "Anomaly Detection in CPS with Machine Learning Techniques." IEEE Transactions on Industrial Cyber-Physical Systems, 19(3), 115-129.

Yin, X., Chen, T., & Feng, Y. (2021). "Hybrid Deep Learning Models for Anomaly Detection in CPS." Journal of Industrial AI, 9(2), 55-72.

Shi, L., & Liu, J. (2021). "Optimization of CNN Architectures for CPS Security." Journal of Machine Learning Applications, 13(1), 87-98.