Resilience of Federated Learning Against False Data Injection Attacks in Energy Forecasting
Authors:
- 17 January 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 245-249
Abstract
Federated learning (FL) has established itself as a communication-efficient, privacy-aware, and cost-effective technique for training machine learning models in energy forecasting. This approach enables simultaneous model training across multiple smart grids while keeping data decentralized at edge nodes. However, FL is not immune to backdoor adversarial attacks, such as data and model poisoning. In this paper, we scrutinize the impact of two data poisoning techniques: scaling and random noise effects. The attack was initiated on one client among ten. As the attack percentage increases, the Mean Absolute Percentage Error (MAPE) of the local model also rises. Our simulation results reveal that the scaling effect elevated MAPE from 0.193% to 32.72%, while random noise increased MAPE from 0.183% to 129.75% as the attacked percentage rose from 10% to 100%. It is concluded that data poisoning solely affects the local model and does not significantly impact the global model; hence, it can provide more resilience than centralized machine learning models.Keywords
This publication has 18 references indexed in Scilit:
- FedTCR: communication-efficient federated learning via taming computing resourcesComplex & Intelligent Systems, 2023
- FedClamp: An Algorithm for Identification of Anomalous Client in Federated Learning2022
- Energy Management in an Agile Workspace using AI-driven Forecasting and Anomaly Detection2022
- CBFL: A Communication-Efficient Federated Learning Framework From Data Redundancy PerspectiveIEEE Systems Journal, 2021
- A Taxonomy of Attacks on Federated LearningIEEE Security & Privacy, 2020
- A review of applications in federated learningComputers & Industrial Engineering, 2020
- Energy Forecasting: A Review and OutlookIEEE Open Access Journal of Power and Energy, 2020
- Electrical Load Forecasting Using Edge Computing and Federated Learning2020
- Energy Demand Prediction with Federated Learning for Electric Vehicle Networks2019
- Forecasting of Intermittent Solar Energy Resource2018