/EECS6322-Course-Project

This project replicates a deep learning-focused paper's central claim to determine if its reported results are reproducible. The core methods and experiments will be re-implemented, and if the results are not reproducible, the reasons for the discrepancy will be explained.

Primary LanguageJupyter Notebook

On the Resiliency of Power and Gas Integration Resources Against Cyber Attacks

Authors

Abstract

This proposal highlights the main contribution of the paper titled "On the Resiliency of Power and Gas Integration Resources Against Cyber Attacks" and its relevance to the EECS6322 course. The paper proposes a cybersecurity framework that leverages machine learning, specifically neural networks, to protect against cyberattacks. The framework aims to secure both field sensor data and information exchanged between power utilities and control panels. To achieve this, the paper employs convolutional neural networks and wavelet transforms to safeguard primary field measurements. Additionally, an unsupervised classification neural network is used to detect the exact operation point of the control signals shared from the power utility. The output of this network is then utilized by a second neural network to determine the exact operation point and identify potential cyberattacks in the power utility's information.

How to run

Preparing the environment

Clone this repository

gh repo clone morekaccino/EECS6322-Course-Project

Create a virtual environment

python -m venv venv

Activate the newly created environment

  • Windows
.\venv\Scripts\activate
  • MacOS / Linux
source venv/bin/activate

Install the requirements

pip install -r requirements.txt

References

  1. W. Schwab and M. Poujol, “The state of industrial cybersecurity 2018,” Trend Study Kaspersky Reports, vol. 33, 2018.
  2. J. Larsen, “Breakage,” Black Hat Federal, 2008.
  3. C. I. Cybersecurity, “Framework for improving critical infrastructure cybersecurity,” URL: https://nvlpubs.nist.gov/nistpubs/CSWP/NIST.CSWP, vol. 4162018, 2018.
  4. V. Y. Pillitteri, T. L. Brewer et al., “Guidelines for smart grid cyberse- curity,” 2014.
  5. M. Mohammadi, Y. Noorollahi, B. Mohammadi-ivatloo, M. Hossein- zadeh, H. Yousefi, and S. T. Khorasani, “Optimal management of energy hubs and smart energy hubs–a review,” Renewable and Sustainable Energy Reviews, vol. 89, pp. 33–50, 2018.
  6. S. Pazouki, E. Naderi, and A. Asrari, “A remedial action framework against cyberattacks targeting energy hubs integrated with distributed energy resources,” Applied Energy, vol. 304, p. 117895, 2021.
  7. A. S. Musleh, G. Chen, and Z. Y. Dong, “A survey on the detection algo- rithms for false data injection attacks in smart grids,” IEEE Transactions on Smart Grid, vol. 11, no. 3, pp. 2218–2234, 2019.
  8. Y. Liu, P. Ning, and M. K. Reiter, “False data injection attacks against state estimation in electric power grids,” ACM Transactions on Informa- tion and System Security (TISSEC), vol. 14, no. 1, pp. 1–33, 2011.
  9. A. Dagoumas, “Assessing the impact of cybersecurity attacks on power systems,” Energies, vol. 12, no. 4, p. 725, 2019.
  10. A. I. Abubakar, H. Chiroma, S. A. Muaz, and L. B. Ila, “A review of the advances in cyber security benchmark datasets for evaluating data- driven based intrusion detection systems,” Procedia Computer Science, vol. 62, pp. 221–227, 2015.
  11. W.-T. Lin, G. Chen, and Y. Huang, “Incentive edge-based federated learning for false data injection attack detection on power grid state estimation: A novel mechanism design approach,” Applied Energy, vol. 314, p. 118828, 2022.
  12. S. A. Salloum, M. Alshurideh, A. Elnagar, and K. Shaalan, “Machine learning and deep learning techniques for cybersecurity: a review,” in Proceedings of the International Conference on Artificial Intelligence and Computer Vision (AICV2020). Springer, 2020, pp. 50–57.
  13. A. M. Sawas, H. Khani, and H. E. Farag, “On the resiliency of power and gas integration resources against cyber attacks,” IEEE Transactions on Industrial Informatics, vol. 17, no. 5, pp. 3099–3110, 2020