Load Redistribution Attack Detection using Machine Learning: A Data-Driven Approach

Andrea Pinceti, Lalitha Sankar, Oliver Kosut

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Three detection techniques are presented against a wide class of cyber-attacks that maliciously redistribute loads by modifying measurements. The detectors use different anomaly detection algorithms based on machine learning techniques: nearest neighbor method, support vector machines, and replicator neural networks. The detectors are tested using a data-driven approach on a realistic dataset comprised of real historical load data in the form of publicly available PJM zonal data mapped to the IEEE 30-bus system. The results show all three detectors to be very accurate, with the nearest neighbor algorithm being the most computational efficient.

Original languageEnglish (US)
Title of host publication2018 IEEE Power and Energy Society General Meeting, PESGM 2018
PublisherIEEE Computer Society
Volume2018-August
ISBN (Electronic)9781538677032
DOIs
StatePublished - Dec 21 2018
Event2018 IEEE Power and Energy Society General Meeting, PESGM 2018 - Portland, United States
Duration: Aug 5 2018Aug 10 2018

Other

Other2018 IEEE Power and Energy Society General Meeting, PESGM 2018
CountryUnited States
CityPortland
Period8/5/188/10/18

Fingerprint

Learning systems
Detectors
Support vector machines
Neural networks

Keywords

  • Cybersecurity
  • False data injection (FDI) attack
  • Load redistribution attack
  • Machine learning
  • Neural network

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Nuclear Energy and Engineering
  • Renewable Energy, Sustainability and the Environment
  • Electrical and Electronic Engineering

Cite this

Pinceti, A., Sankar, L., & Kosut, O. (2018). Load Redistribution Attack Detection using Machine Learning: A Data-Driven Approach. In 2018 IEEE Power and Energy Society General Meeting, PESGM 2018 (Vol. 2018-August). [8586644] IEEE Computer Society. https://doi.org/10.1109/PESGM.2018.8586644

Load Redistribution Attack Detection using Machine Learning : A Data-Driven Approach. / Pinceti, Andrea; Sankar, Lalitha; Kosut, Oliver.

2018 IEEE Power and Energy Society General Meeting, PESGM 2018. Vol. 2018-August IEEE Computer Society, 2018. 8586644.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Pinceti, A, Sankar, L & Kosut, O 2018, Load Redistribution Attack Detection using Machine Learning: A Data-Driven Approach. in 2018 IEEE Power and Energy Society General Meeting, PESGM 2018. vol. 2018-August, 8586644, IEEE Computer Society, 2018 IEEE Power and Energy Society General Meeting, PESGM 2018, Portland, United States, 8/5/18. https://doi.org/10.1109/PESGM.2018.8586644
Pinceti A, Sankar L, Kosut O. Load Redistribution Attack Detection using Machine Learning: A Data-Driven Approach. In 2018 IEEE Power and Energy Society General Meeting, PESGM 2018. Vol. 2018-August. IEEE Computer Society. 2018. 8586644 https://doi.org/10.1109/PESGM.2018.8586644
Pinceti, Andrea ; Sankar, Lalitha ; Kosut, Oliver. / Load Redistribution Attack Detection using Machine Learning : A Data-Driven Approach. 2018 IEEE Power and Energy Society General Meeting, PESGM 2018. Vol. 2018-August IEEE Computer Society, 2018.
@inproceedings{cefff4e097dd465689f6a818a75ebfb0,
title = "Load Redistribution Attack Detection using Machine Learning: A Data-Driven Approach",
abstract = "Three detection techniques are presented against a wide class of cyber-attacks that maliciously redistribute loads by modifying measurements. The detectors use different anomaly detection algorithms based on machine learning techniques: nearest neighbor method, support vector machines, and replicator neural networks. The detectors are tested using a data-driven approach on a realistic dataset comprised of real historical load data in the form of publicly available PJM zonal data mapped to the IEEE 30-bus system. The results show all three detectors to be very accurate, with the nearest neighbor algorithm being the most computational efficient.",
keywords = "Cybersecurity, False data injection (FDI) attack, Load redistribution attack, Machine learning, Neural network",
author = "Andrea Pinceti and Lalitha Sankar and Oliver Kosut",
year = "2018",
month = "12",
day = "21",
doi = "10.1109/PESGM.2018.8586644",
language = "English (US)",
volume = "2018-August",
booktitle = "2018 IEEE Power and Energy Society General Meeting, PESGM 2018",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Load Redistribution Attack Detection using Machine Learning

T2 - A Data-Driven Approach

AU - Pinceti, Andrea

AU - Sankar, Lalitha

AU - Kosut, Oliver

PY - 2018/12/21

Y1 - 2018/12/21

N2 - Three detection techniques are presented against a wide class of cyber-attacks that maliciously redistribute loads by modifying measurements. The detectors use different anomaly detection algorithms based on machine learning techniques: nearest neighbor method, support vector machines, and replicator neural networks. The detectors are tested using a data-driven approach on a realistic dataset comprised of real historical load data in the form of publicly available PJM zonal data mapped to the IEEE 30-bus system. The results show all three detectors to be very accurate, with the nearest neighbor algorithm being the most computational efficient.

AB - Three detection techniques are presented against a wide class of cyber-attacks that maliciously redistribute loads by modifying measurements. The detectors use different anomaly detection algorithms based on machine learning techniques: nearest neighbor method, support vector machines, and replicator neural networks. The detectors are tested using a data-driven approach on a realistic dataset comprised of real historical load data in the form of publicly available PJM zonal data mapped to the IEEE 30-bus system. The results show all three detectors to be very accurate, with the nearest neighbor algorithm being the most computational efficient.

KW - Cybersecurity

KW - False data injection (FDI) attack

KW - Load redistribution attack

KW - Machine learning

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=85060784898&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060784898&partnerID=8YFLogxK

U2 - 10.1109/PESGM.2018.8586644

DO - 10.1109/PESGM.2018.8586644

M3 - Conference contribution

AN - SCOPUS:85060784898

VL - 2018-August

BT - 2018 IEEE Power and Energy Society General Meeting, PESGM 2018

PB - IEEE Computer Society

ER -