Published Paper Details:

The SCADA system, crucial for monitoring smart grid performance, faces cyber threats due to weak communication protocol protection. Hackers exploit these vulnerabilities to inject false data, causing delayed detection and posing risks of infrastructure damage and fatalities. This study proposes the MSPPNet algorithm to identify and classify cyber attacks, utilizing deep learning and metaheuristic optimization. Evaluation on a dataset from Mississippi State University's Oak Ridge National Laboratory compares MSPPNet with traditional supervised learning methods. Results reveal MSPPNet's superior performance, achieving an 82% accuracy in binary classification. This algorithm enhances security in SCADA systems, mitigating risks of false data injection and deceptive manipulation by attackers. By leveraging advanced machine learning techniques, this research contributes to safeguarding critical infrastructure and ensuring the reliability and safety of smart grids.