• Paper Title: A Noise-Removal Machine Learning Approach for Enhanced Threats Detection in ICS Networks
  • Conference Name: The Korean Institute of Communications and Information Sciences (KICS) 2024
  • Abstract: The centralised and vulnerable nature of industrial control system (ICS) networks, attracts malicious actors seeking to exploit vulnerabilities, compromise data and disrupt critical processes. Current threat detection methods overlook real-world noise disturbances experienced in industrial processes, leading to sub-optimal model performance. This study introduces a security framework that can be deployed at the supervisory part of ICS, to handle noisy traffic from industrial processing, ensuring an effective attack detection. Experimental simulations validate its effectiveness when compared with state-of-the-art based on key performance metrics.
  • Status: Accepted
  • Conference Type: Domestic
  • Cite: Urslla Uchechi Izuazu, Vivan Ukamaka Ihekoronye, Dong-Seong Kim, Jae Min Lee"A noise removal Machine Learning Approach for Enhanced Threats Detection in ICS Networks" The Korean Institute of Communications and Information Sciences (KICS) 2024
  • Author: uursla8
  • Write Date: Feb. 13, 2024, 7:31 a.m.
  • Update Date: Feb. 13, 2024, 7:31 a.m.
  • Visit Count: 1
  • Acknowledgment: This work was partly supported by Innovative Human Resource Development for Local Intellectualizatio
  • File: No file attached