A Machine Learning Approach to Detecting and Preventing Intrusion Attacks
Open Access DepositedEnhancing Security Measures in Electrical Control Systems
The electrical grid is one of the most crucial elements in industrial infrastructure since it plays a central role in energy supply to various sectors. Due to its importance and intrinsic vulnerabilities, the electrical grid has become one of the favorite targets for highly sophisticated cyberattacks. In particular, these have grown very much recently, since the first confirmed cyberattack on Ukraine's power grid (International Energy Agency, 2021).Integrated Industrial Internet of Things devices (IIoT) that become part of electrical grids are predominantly sensors and control electronics. Though these devices are very much required to control and monitor electrical systems, they have less computational power and therefore are resource-constrained devices
comparing existing learning algorithms with newly implemented models and comparing models with industrial-specific features.
thus, these devices are prone to cyber attack. With the rise of sophisticated cybersecurity attacks, traditional security mechanisms have failed to provide robust protection for these devices. Besides, the available machine learning models based on generic IoT and network-related features are not good enough to meet the security requirements of industrial control systems (Neto et al., 2023). In this regard, this research will develop a machine learning-based intrusion detection system that uses industrial-specific features introduced in the CICAPTIIoT2024 dataset (Ghiasvand et al., 2024). The proposed models aim to enhance the accuracy and efficiency of detecting cyberattacks on electrical control systems using tailored features. This work will compare the performance of different machine learning algorithms with those applied in related works. Comparative analysis will be performed in two directions
- All rights reserved
Notice to Authors
If you are the author of this work and you have any questions about the information on this page, please use the Contact form to get in touch with us.
| Thumbnail | Title | Date Uploaded | Visibility | Actions |
|---|---|---|---|---|
|
|
Qasaimeh_gwu_0075A_17403.pdf | 2025-12-12 | Open Access |
|