Leveraging Machine Learning for SCADA-based Smart Grids Security

In the evolving landscape of smart grids (SGs), Supervisory Control and Data Acquisition (SCADA) systems play a pivotal role in ensuring the seamless operation of power networks. However, their critical nature makes them a prime target for cyberattacks, particularly Man-in-the-Middle (MIM) attacks, which can disrupt grid stability and security. This paper proposes a machine learning (ML) model based on a decision tree (DT) to enhance the resilience of SCADA systems within SGs to detect and mitigate MIM attacks, thereby safeguarding the integrity and reliability of SG operations. The obtained results demonstrate the effectiveness of the proposed approach in identifying and responding to potential security threats. The proposed model is examined by six evaluation metrics namely, accuracy, F -score, kappa score, elapsed time, learning curve, and confusion matrix. The proposed DT classifier outperformed the benchmarks achieving an accuracy of 100 %.