Detecting and Mitigating Adversarial Examples in Regression Tasks: A Photovoltaic Power Generation Forecasting Case Study
Open Access
- 26 September 2021
- journal article
- research article
- Published by MDPI AG in Information
- Vol. 12 (10) , 394
Abstract
With data collected by Internet of Things sensors, deep learning (DL) models can forecast the generation capacity of photovoltaic (PV) power plants. This functionality is especially relevant for PV power operators and users as PV plants exhibit irregular behavior related to environmental conditions. However, DL models are vulnerable to adversarial examples, which may lead to increased predictive error and wrong operational decisions. This work proposes a new scheme to detect adversarial examples and mitigate their impact on DL forecasting models. This approach is based on one-class classifiers and features extracted from the data inputted to the forecasting models. Tests were performed using data collected from a real-world PV power plant along with adversarial samples generated by the Fast Gradient Sign Method under multiple attack patterns and magnitudes. One-class Support Vector Machine and Local Outlier Factor were evaluated as detectors of attacks to Long-Short Term Memory and Temporal Convolutional Network forecasting models. According to the results, the proposed scheme showed a high capability of detecting adversarial samples with an average F1-score close to 90%. Moreover, the detection and mitigation approach strongly reduced the prediction error increase caused by adversarial samples.Keywords
Funding Information
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (Finance code 001)
- Conselho Nacional de Desenvolvimento Científico e Tecnológico (420562/2018-4, 440045/2020-7, 309863/2020-1)
- Amazon Web Services (CNPq/AWS 032/2019)
This publication has 38 references indexed in Scilit:
- Wild patterns: Ten years after the rise of adversarial machine learningPattern Recognition, 2018
- Forecasting of photovoltaic power generation and model optimization: A reviewRenewable and Sustainable Energy Reviews, 2018
- MagNet2017
- SafetyNet: Detecting and Rejecting Adversarial Examples Robustly2017
- Review of photovoltaic power forecastingSolar Energy, 2016
- Adversarial Diversity and Hard Positive Generation2016
- Distillation as a Defense to Adversarial Perturbations Against Deep Neural Networks2016
- Long Short-Term MemoryNeural Computation, 1997
- Support-vector networksMachine Learning, 1995
- An Approach to Time Series AnalysisThe Annals of Mathematical Statistics, 1961