Visible to the public Poisoning Attack on Load Forecasting

TitlePoisoning Attack on Load Forecasting
Publication TypeConference Paper
Year of Publication2019
AuthorsLiang, Y., He, D., Chen, D.
Conference Name2019 IEEE Innovative Smart Grid Technologies - Asia (ISGT Asia)
Date PublishedMay 2019
ISBN Number978-1-7281-3520-5
KeywordsAI Poisoning, closed-form solution, Data models, data poisoning strategy, Forecasting, Global Energy Forecasting Competition data, Human Behavior, load forecasting, Load modeling, MLR attacking solution, MLR model, multiple linear regression, Neural Network, Numerical models, Outlier detection, poisoning attack, poisoning attack solution, power engineering computing, power grids, power system security, Predictive models, pubcrawl, regression analysis, resilience, Resiliency, Scalability, security of data, short-term load forecasting systems, simulated annealing, statistical methods, Training data

Short-term load forecasting systems for power grids have demonstrated high accuracy and have been widely employed for commercial use. However, classic load forecasting systems, which are based on statistical methods, are subject to vulnerability from training data poisoning. In this paper, we demonstrate a data poisoning strategy that effectively corrupts the forecasting model even in the presence of outlier detection. To the best of our knowledge, poisoning attack on short-term load forecasting with outlier detection has not been studied in previous works. Our method applies to several forecasting models, including the most widely-adapted and best-performing ones, such as multiple linear regression (MLR) and neural network (NN) models. Starting with the MLR model, we develop a novel closed-form solution to quickly estimate the new MLR model after a round of data poisoning without retraining. We then employ line search and simulated annealing to find the poisoning attack solution. Furthermore, we use the MLR attacking solution to generate a numerical solution for other models, such as NN. The effectiveness of our algorithm has been tested on the Global Energy Forecasting Competition (GEFCom2012) data set with the presence of outlier detection.

Citation Keyliang_poisoning_2019