Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Performance Evaluation of Vertical Federated Machine Learning Against Adversarial Threats on Wide-Area Control System

Conference ·
; ;
Federated machine learning (FL) is gaining significant popularity to develop cybersecurity solutions in power grids because of its advanced capability to support decentralized data handing at local devices, its privacy preservation, and its low-bandwidth requirement. However, the evolving adversarial machine learning (AML) threats raise significant concerns for the cybersecurity of FL architectures. The FL-based split neural network (SplitNN) achieves high performance through the decentralized training of local neural network models while preserving data privacy across multiple entities. In this paper, we propose a methodology for evaluating the performance of a vertical FL-based anomaly detector against different types of AML attacks, including denial-of-service attacks, adversarial data injection attacks, and replay attacks on the trained local models deployed in the grid network. For a case study, we consider the modified IEEE 13-bus system, and we develop SplitNN-based binary and multiclass classification models to detect, locate, and identify different types of data integrity attacks on the volt-watt control with two pooling layers: maximum pooling and AvgPool. Our experimental results, computed through performance metrics, reveal that the severity of these AML attacks varies with the integrated pooling mechanism, the type of classification model, and the nature of the cyberattack. Further, the AML attacks negatively impacted the prediction time per sample for the pretrained SplitNN during the online testing.
Research Organization:
National Renewable Energy Laboratory (NREL), Golden, CO (United States)
Sponsoring Organization:
USDOE National Renewable Energy Laboratory (NREL), Laboratory Directed Research and Development (LDRD) Program
DOE Contract Number:
AC36-08GO28308
OSTI ID:
2524545
Report Number(s):
NREL/CP-5T00-93502; MainId:95284; UUID:4fe25465-86d3-46de-9e34-412c9789f188; MainAdminId:76211
Country of Publication:
United States
Language:
English

References (13)

A Cyber-Physical Anomaly Detection for Wide-Area Protection using Machine Learning journal January 2021
Stealthy cyber attacks and impact analysis on wide-area protection of smart grid conference September 2016
A Federated Learning Framework for Detecting False Data Injection Attacks in Solar Farms journal March 2022
Hierarchical models of object recognition in cortex journal November 1999
Stuxnet worm impact on industrial cyber-physical system security
  • Karnouskos, Stamatis
  • IECON 2011 - 37th Annual Conference of IEEE Industrial Electronics, IECON 2011 - 37th Annual Conference of the IEEE Industrial Electronics Society https://doi.org/10.1109/IECON.2011.6120048
conference November 2011
Hacking Power Grids: A Current Problem journal December 2017
Distributed Anomaly Detection in Smart Grids: A Federated Learning-Based Approach journal January 2023
SHARP-Net: Platform for Self-Healing and Attack Resilient PMU Networks conference February 2020
An integrated federated learning algorithm for short-term load forecasting journal January 2023
Federated Machine Learning-Based Anomaly Detection System for Synchrophasor Network Using Heterogeneous Data Sets conference May 2024
Detection of replay attacks in smart grid systems conference January 2013
A survey on security and privacy threats to federated learning conference October 2021
Denial-of-service attack-detection techniques journal January 2006

Similar Records

Related Subjects

MATHEMATICS AND COMPUTING
POWER TRANSMISSION AND DISTRIBUTION
adversarial threats
cybersecurity
federated machine learning
power grid
split neural network