Stealthy MTD against unsupervised learning-based blind FDI Attacks in power systems
File(s)
Published version
Author(s)
Higgins, Martin
Teng, Fei
Parisini, Thomas
Type
Journal Article
Abstract
This paper examines how moving target defenses (MTD) implemented in power systems can be countered by unsupervised learning-based false data injection (FDI) attack and how MTD can be combined with physical watermarking to enhance the system resilience. A novel intelligent attack, which incorporates dimensionality reduction and density-based spatial clustering, is developed and shown to be effective in maintaining stealth in the presence of traditional MTD strategies. In resisting this new type of attack, a novel implementation of MTD combining with physical watermarking is proposed by adding Gaussian watermark into physical plant parameters to drive detection of traditional and intelligent FDI attacks, while remaining hidden to the attackers and limiting the impact on system operation and stability.
Date Issued
2020-09-28
Date Acceptance
2020-09-16
Citation
IEEE Transactions on Information Forensics and Security, 2020, 16, pp.1275-1287
ISSN
1556-6013
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Start Page
1275
End Page
1287
Journal / Book Title
IEEE Transactions on Information Forensics and Security
Volume
16
Copyright Statement
© 2020 The Author(s). This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
License URL
Sponsor
Economic & Social Research Council (ESRC)
Identifier
https://ieeexplore.ieee.org/document/9207760
Grant Number
ES/T000112/1
Subjects
Strategic, Defence & Security Studies
08 Information and Computing Sciences
09 Engineering
Publication Status
Published
Date Publish Online
2020-09-28