The Best Paper Award at the Resilience Week Symposium, held in San Antonio, Texas, was awarded to researchers from ISIS/Vanderbilt University. The title of the paper is "Evaluating Resilience of Grid Load Predictions under Stealthy Adversarial Attacks" and was authored by Xingyu Zhou, Yi Li, Carlos A. Barreto, Jiani Li, Peter Volgyesi, Dr. Himanshu Neema, and Dr. Xenofon Koutsoukos. The Resilience Week Best Paper Award recognizes the paper that exhibits key contributions in the field of Cyber-Physical Resilience of the Electric Grid. The best paper was nominated by the Resilience Week Symposium organizing committee.

Recent advances in machine learning enable wider applications of prediction models in cyber-physical systems. Smart grids are increasingly using distributed sensor settings for distributed sensor fusion and information processing. Load forecasting systems use these sensors to predict future loads to incorporate into dynamic pricing of power and grid maintenance. However, these inference predictors are highly complex and thus vulnerable to adversarial attacks. Moreover, the adversarial attacks are synthetic norm-bounded modifications to a limited number of sensors that can greatly affect the accuracy of the overall predictor. It can be much cheaper and effective to incorporate elements of security and resilience at the earliest stages of design. In this paper, we demonstrate how to analyze the security and resilience of learning-based prediction models in power distribution networks by utilizing a domain-specific deep-learning and testing framework. This framework is developed using DeepForge and enables rapid design and analysis of attack scenarios against distributed smart meters in a power distribution network. It runs the attack simulations in the cloud backend. In addition to the predictor model, we have integrated an anomaly detector to detect adversarial attacks targeting the predictor. We formulate the stealthy adversarial attacks as an optimization problem to maximize prediction loss while minimizing the required perturbations. Under the worst-case setting, where the attacker has full knowledge of both the predictor and the detector, an iterative attack method has been developed to solve for the adversarial perturbation. We demonstrate the framework capabilities using a GridLAB-D based power distribution network model and show how stealthy adversarial attacks can affect smart grid prediction systems even with a partial control of network.

Xingyu Zhou is a graduate student at the Institute for Software Integrated Systems (ISIS) in the Department of EECS at Vanderbilt. Yi Li has recently completed his PhD from Vanderbilt under Prof. Eugene Vorobeychik. Carlos A. Barreto is a post graduate research at ISIS under Dr. Xenofon Koutsoukos. Jiani Li is a graduate student under Dr. Xenofon Koutsoukos. Peter Volgyesi is a research scientist at ISIS. Dr. Himanshu Neema is a Research Assistant Professor of Computer Science at Vanderbilt. Dr. Xenofon Koutsoukos is a Professor of Computer Science, Computer Engineering, and Electrical Engineering. Dr. Koutsoukos is also the Associate Chair of the EECS Department at Vanderbilt.