Real-Time Cyber-Physical False Data Attack Detection in Smart Grids Using Neural Networks

Erik M. Ferragut; Jason Laska; Mohammed M. Olama; Ozgur Ozmen

doi:10.1109/CSCI.2017.1

Real-Time Cyber-Physical False Data Attack Detection in Smart Grids Using Neural Networks

Erik M. Ferragut, Jason Laska, Mohammed M. Olama, Ozgur Ozmen

Computational Systems Engineering and Cy

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

36 Scopus citations

Abstract

Attacks on cyber-physical systems have recently increased in frequency, impact, and publicity. In this paper, a cyber-physical false data attack detection mechanism is proposed to protect the operation of power transmission and distribution systems by automatically inferring underlying physical relationships using cross-sensor analytics in order to detect sensor failures, replay attacks, and other data integrity issues in real-time. We investigate a neural network based mechanism acting on voltage and current readings resulting from a wide variety of load conditions on the IEEE 30-bus power system standard and compare its performance with a support vector machine based mechanism. Experiments showed that 99% detection accuracy of replay attacks was achieved using the proposed neural network mechanism. More importantly, we showed that the best approach was to not create physics-based features using what we knew about the system, but rather to use a neural network to automatically learn the laws, and then use the outputs of that to build a classifier to identify whether and where data spoofing occurs. Thus, it is preferable to infer and exploit the physics using a single machine learning solution rather than to add features first and then build a detector.

Original language	English
Title of host publication	Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017
Editors	Fernando G. Tinetti, Quoc-Nam Tran, Leonidas Deligiannidis, Mary Qu Yang, Mary Qu Yang, Hamid R. Arabnia
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-6
Number of pages	6
ISBN (Electronic)	9781538626528
DOIs	https://doi.org/10.1109/CSCI.2017.1
State	Published - Dec 4 2018
Event	2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017 - Las Vegas, United States Duration: Dec 14 2017 → Dec 16 2017

Publication series

Name	Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017

Conference

Conference	2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017
Country/Territory	United States
City	Las Vegas
Period	12/14/17 → 12/16/17

Funding

This work has been partially supported by the Department of Homeland Security (DHS) Science and Technology Directorate, Homeland Security Advanced Research Projects Agency, Cyber Security Division under the Transition to Practice (TTP) program. The views expressed in this work are strictly those of the authors and do not necessarily reflect the official policy or position of any funding agency. ACKNOWLEDGMENT Research sponsored by the Laboratory Directed Research and Development Program of Oak Ridge National Laboratory, managed by UT-Battelle, LLC, for the U. S. Department of Energy. The submitted manuscript has been authored by a contractor of the U.S. Government under Contract DE-AC05-00OR22725. Accordingly, the U.S. Government retains a nonexclusive, royalty-free license to publish or reproduce the published form of this contribution, or allow others to do so, for U.S. Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan.

Keywords

Cyber-physical systems
IEEE 30-bus power system
cybersecurity
integrity attacks
neural networks
replay attacks
smart grids
support vector machine

Access to Document

10.1109/CSCI.2017.1

Cite this

Ferragut, E. M., Laska, J., Olama, M. M., & Ozmen, O. (2018). Real-Time Cyber-Physical False Data Attack Detection in Smart Grids Using Neural Networks. In F. G. Tinetti, Q.-N. Tran, L. Deligiannidis, M. Q. Yang, M. Q. Yang, & H. R. Arabnia (Eds.), Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017 (pp. 1-6). Article 8560712 (Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CSCI.2017.1

Ferragut, Erik M. ; Laska, Jason ; Olama, Mohammed M. et al. / Real-Time Cyber-Physical False Data Attack Detection in Smart Grids Using Neural Networks. Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017. editor / Fernando G. Tinetti ; Quoc-Nam Tran ; Leonidas Deligiannidis ; Mary Qu Yang ; Mary Qu Yang ; Hamid R. Arabnia. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-6 (Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017).

@inproceedings{7b8796152f094f639b27f1a94448debc,

title = "Real-Time Cyber-Physical False Data Attack Detection in Smart Grids Using Neural Networks",

abstract = "Attacks on cyber-physical systems have recently increased in frequency, impact, and publicity. In this paper, a cyber-physical false data attack detection mechanism is proposed to protect the operation of power transmission and distribution systems by automatically inferring underlying physical relationships using cross-sensor analytics in order to detect sensor failures, replay attacks, and other data integrity issues in real-time. We investigate a neural network based mechanism acting on voltage and current readings resulting from a wide variety of load conditions on the IEEE 30-bus power system standard and compare its performance with a support vector machine based mechanism. Experiments showed that 99% detection accuracy of replay attacks was achieved using the proposed neural network mechanism. More importantly, we showed that the best approach was to not create physics-based features using what we knew about the system, but rather to use a neural network to automatically learn the laws, and then use the outputs of that to build a classifier to identify whether and where data spoofing occurs. Thus, it is preferable to infer and exploit the physics using a single machine learning solution rather than to add features first and then build a detector.",

keywords = "Cyber-physical systems, IEEE 30-bus power system, cybersecurity, integrity attacks, neural networks, replay attacks, smart grids, support vector machine",

author = "Ferragut, {Erik M.} and Jason Laska and Olama, {Mohammed M.} and Ozgur Ozmen",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017 ; Conference date: 14-12-2017 Through 16-12-2017",

year = "2018",

month = dec,

day = "4",

doi = "10.1109/CSCI.2017.1",

language = "English",

series = "Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1--6",

editor = "Tinetti, {Fernando G.} and Quoc-Nam Tran and Leonidas Deligiannidis and Yang, {Mary Qu} and Yang, {Mary Qu} and Arabnia, {Hamid R.}",

booktitle = "Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017",

}

Ferragut, EM, Laska, J, Olama, MM & Ozmen, O 2018, Real-Time Cyber-Physical False Data Attack Detection in Smart Grids Using Neural Networks. in FG Tinetti, Q-N Tran, L Deligiannidis, MQ Yang, MQ Yang & HR Arabnia (eds), Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017., 8560712, Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017, Institute of Electrical and Electronics Engineers Inc., pp. 1-6, 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017, Las Vegas, United States, 12/14/17. https://doi.org/10.1109/CSCI.2017.1

Real-Time Cyber-Physical False Data Attack Detection in Smart Grids Using Neural Networks. / Ferragut, Erik M.; Laska, Jason; Olama, Mohammed M. et al.
Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017. ed. / Fernando G. Tinetti; Quoc-Nam Tran; Leonidas Deligiannidis; Mary Qu Yang; Mary Qu Yang; Hamid R. Arabnia. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-6 8560712 (Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Real-Time Cyber-Physical False Data Attack Detection in Smart Grids Using Neural Networks

AU - Ferragut, Erik M.

AU - Laska, Jason

AU - Olama, Mohammed M.

AU - Ozmen, Ozgur

PY - 2018/12/4

Y1 - 2018/12/4

N2 - Attacks on cyber-physical systems have recently increased in frequency, impact, and publicity. In this paper, a cyber-physical false data attack detection mechanism is proposed to protect the operation of power transmission and distribution systems by automatically inferring underlying physical relationships using cross-sensor analytics in order to detect sensor failures, replay attacks, and other data integrity issues in real-time. We investigate a neural network based mechanism acting on voltage and current readings resulting from a wide variety of load conditions on the IEEE 30-bus power system standard and compare its performance with a support vector machine based mechanism. Experiments showed that 99% detection accuracy of replay attacks was achieved using the proposed neural network mechanism. More importantly, we showed that the best approach was to not create physics-based features using what we knew about the system, but rather to use a neural network to automatically learn the laws, and then use the outputs of that to build a classifier to identify whether and where data spoofing occurs. Thus, it is preferable to infer and exploit the physics using a single machine learning solution rather than to add features first and then build a detector.

AB - Attacks on cyber-physical systems have recently increased in frequency, impact, and publicity. In this paper, a cyber-physical false data attack detection mechanism is proposed to protect the operation of power transmission and distribution systems by automatically inferring underlying physical relationships using cross-sensor analytics in order to detect sensor failures, replay attacks, and other data integrity issues in real-time. We investigate a neural network based mechanism acting on voltage and current readings resulting from a wide variety of load conditions on the IEEE 30-bus power system standard and compare its performance with a support vector machine based mechanism. Experiments showed that 99% detection accuracy of replay attacks was achieved using the proposed neural network mechanism. More importantly, we showed that the best approach was to not create physics-based features using what we knew about the system, but rather to use a neural network to automatically learn the laws, and then use the outputs of that to build a classifier to identify whether and where data spoofing occurs. Thus, it is preferable to infer and exploit the physics using a single machine learning solution rather than to add features first and then build a detector.

KW - Cyber-physical systems

KW - IEEE 30-bus power system

KW - cybersecurity

KW - integrity attacks

KW - neural networks

KW - replay attacks

KW - smart grids

KW - support vector machine

UR - http://www.scopus.com/inward/record.url?scp=85060660364&partnerID=8YFLogxK

U2 - 10.1109/CSCI.2017.1

DO - 10.1109/CSCI.2017.1

M3 - Conference contribution

AN - SCOPUS:85060660364

T3 - Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017

SP - 1

EP - 6

BT - Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017

A2 - Tinetti, Fernando G.

A2 - Tran, Quoc-Nam

A2 - Deligiannidis, Leonidas

A2 - Yang, Mary Qu

A2 - Arabnia, Hamid R.

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017

Y2 - 14 December 2017 through 16 December 2017

ER -

Ferragut EM, Laska J, Olama MM, Ozmen O. Real-Time Cyber-Physical False Data Attack Detection in Smart Grids Using Neural Networks. In Tinetti FG, Tran QN, Deligiannidis L, Yang MQ, Yang MQ, Arabnia HR, editors, Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-6. 8560712. (Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017). doi: 10.1109/CSCI.2017.1

Real-Time Cyber-Physical False Data Attack Detection in Smart Grids Using Neural Networks

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this