Visible to the public Evaluating Resilience of Grid Load Predictions under Stealthy Adversarial Attacks

TitleEvaluating Resilience of Grid Load Predictions under Stealthy Adversarial Attacks
Publication TypeConference Paper
Year of Publication2019
AuthorsZhou, Xingyu, Li, Yi, Barreto, Carlos A., Li, Jiani, Volgyesi, Peter, Neema, Himanshu, Koutsoukos, Xenofon
Conference Name2019 Resilience Week (RWS)
Date Publishednov
Keywordsadversarial attacks, adversarial perturbation, CPS Resilience, cyber physical systems, Cyber-physical systems, Data security, DeepForge, distributed sensor fusion, distributed sensors, distributed smart meters, domain-specific deep-learning, Dynamic Pricing, grid maintenance, GridLAB-D, inference predictors, information processing, iterative attack method, Iterative methods, learning (artificial intelligence), load forecasting, load forecasting systems, machine learning, model-based design, optimisation, optimization problem, power distribution control, power distribution network, power distribution planning, power engineering computing, Power systems, pubcrawl, resilience evaluation, Resiliency, security of data, sensor fusion, smart grid load prediction systems, smart meters, smart power grids, synthetic norm-bounded modifications, testbed
AbstractRecent 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.
Citation Keyzhou_evaluating_2019