Research Article

Convolutional Neural Networks Based Detection System for Cyber-attacks in Industrial Control Systems

Authors

  • MD KHOKAN BHUYAN Department of Business Administration, Westcliff University, 17877 Von Karman Ave 4th floor, Irvine, CA 92614, United States
  • Md Kamruzzaman Department of Business Administration, Westcliff University, California 90020, USA
  • Sadia Islam Nilima Department of Business Administration, International American University, 3440 Wilshire Blvd STE 1000, Los Angeles, CA 90010, United States
  • RABEYA KHATOON Department of Business Administration, International American University, 3440 Wilshire Blvd STE 1000, Los Angeles, CA 90010, United States
  • Nur Mohammad Department of Information Technology, Westcliff University, 17877 Von Karman Ave 4th floor, Irvine, CA 92614, United States

Abstract

Convolutional Neural Networks (CNNs) have emerged as a powerful tool for various pattern recognition tasks, including the detection of cyber-attacks in Industrial Control Systems (ICS). This paper presents a CNN-based detection system specifically designed to safeguard ICS from sophisticated cyber threats. The proposed system leverages the capability of CNNs to automatically learn and extract high-level features from raw data, enabling it to identify anomalies indicative of cyber-attacks with high accuracy. Utilizing a comprehensive cyber-attack dataset containing 59 different types of attacks, the system is trained to distinguish between normal and malicious traffic effectively. Based on the extensive dataset, this study demonstrates that the CNN-based detection system achieves a detection rate of 98.5% and a false-positive rate of 1.2%, significantly outperforming traditional methods. The high detection rate indicates the system's ability to accurately identify a wide range of attack types, while the low false-positive rate ensures minimal disruption to normal operations due to incorrect alerts. These results underscore the system's robustness and reliability in identifying subtle and complex attack patterns. Moreover, the CNN-based system is designed to adapt to new types of attacks as it continues to learn from updated datasets, making it a scalable and future-proof solution. Implementing this system can significantly enhance the cybersecurity posture of industrial environments by providing real-time monitoring and rapid response capabilities. The CNN-based detection system offers a significant advancement in ICS cybersecurity. Effectively identifying and mitigating cyber-attacks contributes to the resilience and reliability of critical infrastructure. The proposed approach improves security measures and ensures industrial processes' continuous and safe operation, which is vital for economic stability and public safety.

Article information

Journal

Journal of Computer Science and Technology Studies

Volume (Issue)

6 (3)

Pages

86-96

Published

2024-08-07

How to Cite

BHUYAN, M. K., Kamruzzaman, M., Nilima , S. I., KHATOON, R., & Mohammad, N. (2024). Convolutional Neural Networks Based Detection System for Cyber-attacks in Industrial Control Systems. Journal of Computer Science and Technology Studies, 6(3), 86–96. https://doi.org/10.32996/jcsts.2024.6.3.9

Downloads

Keywords:

Convolutional Neural Networks (CNNs), Industrial Control Systems (ICS), Cybersecurity, Real-time Monitoring, Critical Infrastructure