Developing Predictive AI Models for Securing U.S. Critical Infrastructure Against Emerging Cyber Threats

Anupom Debnath; Sadia Sharmin; Nur Vanu; Adib Hossain; Muslima Begom Riipa; Anseena Anees  Sabeena; Md Azharul Islam; Arafat Islam; Sanchita Saha

doi:10.63332/joph.v3i3.2585

Authors

Anupom Debnath Department of Business Administration, International American University, Los Angeles, CA 90010, USA
Sadia Sharmin Department of Business Administration, International American University, Los Angeles, CA 90010, USA
Nur Vanu Department of Science in Business Analytics, Trine University, Angola, IN 46703, USA
Adib Hossain Department of Business Analytics, Trine University, Angola, IN 46703, USA
Muslima Begom Riipa Department of Business Administration, International American University, Los Angeles, CA 90010, USA
Anseena Anees Sabeena Department of Business Administration, Westcliff University, Irvine, CA 92614, USA
Md Azharul Islam Department of Business Administration, Westcliff University, Irvine, CA 92614, USA
Arafat Islam Department of Business Analytics, Trine University, Indiana, USA
Sanchita Saha Department of Business Administration, Westcliff University, Irvine, CA 92614, USA

DOI:

https://doi.org/10.63332/joph.v3i3.2585

Keywords:

Smart Grid, Cybersecurity, Artificial Intelligence, Machine Learning, Big Data Risk Assessment

Abstract

Smart grids (SGs) have emerged in the United States as part of the effort to modernize the nation’s aging electricity infrastructure. While existing cybersecurity tools are generally effective at detecting and preventing known threats, they fall short in addressing the growing complexity of advanced cyberattacks. Ensuring robust protection for the U.S. smart grid requires a comprehensive approach that integrates advanced technologies and proactive processes. Leveraging big data analytics, artificial intelligence (AI), and machine learning (ML) enables a more adaptive and holistic security framework. These technologies allow for the identification of new, previously undetected threats by analyzing behavioral patterns and predicting anomalies through intelligent systems. By combining known and unknown threat data, predictive analytics can significantly enhance the cybersecurity posture of critical energy infrastructure. This paper explores current trends and key challenges in safeguarding U.S. smart grids using big data and AI-driven approaches. It includes an overview of smart grid architecture and functionality, highlights technological advancements, and outlines a qualitative risk assessment method. Additionally, it discusses major contributions to improving the reliability, safety, and efficiency of the electric grid, proposes layered security measures, and evaluates cybersecurity risk management strategies for supervisory control and data acquisition (SCADA) systems.