CySER Virtual Seminar – Are Machine Learning Detectors Sufficient? Exploring Cyberattacks and Defense Strategies in Smart Grids

About the event

Title: Are Machine Learning Detectors Sufficient? Exploring Cyberattacks and Defense Strategies in Smart Grids

Speaker: Bo Liu

Abstract: Smart grids integrate information and communication technology (ICT)-enabled devices and Internet of Things (IoT) technologies to support the transition toward decarbonization and electrification. However, the widespread deployment of these devices also introduces cybersecurity vulnerabilities. This seminar will introduce major cyberattacks targeting power systems, emphasizing their potential to disrupt grid operations and cause economic losses. Additionally, various defense strategies will be explored. Given the increasing adoption of machine-learning-based detectors in power systems, this session will assess the limitations of classic machine-learning detectors. The presenter will present a novel method for constructing highly stealthy false data injection attacks that bypass machine-learning detectors. This will enable devising more sophisticated defense strategies.

Speaker Bio: Dr. Bo Liu is an Assistant Professor in the School of Engineering and Applied Science at Washington State University (WSU), Tri-cities, as of August 2024. He received his Ph.D. from the Mike Wiegers Department of Electrical and Computer Engineering at Kansas State University, Manhattan, KS, USA, in 2021, where he also worked as a Postdoc and Research Assistant Professor. He has M.S. and B.S. degrees from Harbin Institute of Technology, China. In the summer of 2018, he was a graduate research intern at the National Renewable Energy Laboratory (NREL). His primary research interests include cyber-physical security of power systems, machine learning applications, and state estimation in smart grids.

Learn more about CySER: https://cyser.wsu.edu/