AI and Hardware Security for resilient Electric Power Systems
Research in the Hardware and Embedded Design and Security (HEADS) lab focuses on hardware-based authentication framework using strong physical unclonable functions (PUFs), new authentication techniques, incorporating lightweight cryptographic primitives, and novel pre-boot authentication and storage encryption functions for trusted platform modules (TPM). Recent research develops, validates, and demonstrates CyberPREPS, a concurrent learning cyber-physical framework for resilient electric power transmission and distribution systems. The project evaluates cross-layer vulnerability assessment and security for anomaly detection and localization and side channel resilient design for energy delivery transmission and distribution process to develop a suite of concurrent learning resilient algorithms. The developed algorithms seamlessly merge data-driven machine learning models, for the cyber layer, with domain knowledge physics-based models, for the physical layer, to simultaneously achieve high accuracy and high generalizability for detecting, localizing, and neutralizing both known and unknown cyberattacks. For additional details on this project and other lab activities please click here.