Dr. Mahmoud Badr, Assistant Professor of Network and Computer Security at SUNY Polytechnic Institute and the MS Cybersecurity Graduate Coordinator, has published new research in the IEEE Internet of Things Journal (Q1, with an impact factor of 8.2), titled, 'Securing Smart Grid False Data Detectors Against White-Box Evasion Attacks Without Sacrificing Accuracy.' The research focuses on the vulnerabilities of smart grid systems to cyberattacks and is a direct result of the ongoing project 'Enhancing Security and Privacy in Smart Power Grids,' led by Dr. Badr.

His study specifically addresses how gradient-ensemble-based evasion attacks can undermine machine learning (ML)-based electricity theft detectors, a critical challenge for the stability of smart grids. The research introduces a novel approach combining clustering, adversarial training, and ensemble methods to improve the robustness and accuracy of these detectors, advancing the field of smart grid security. This is significant because it tackles a critical vulnerability in smart grids—cyberattacks on ML-based detectors designed to identify electricity theft. With the rise of advanced evasion attacks, traditional detection models face challenges in distinguishing between legitimate and manipulated data.