Efficient detection of electricity theft cyber attacks in AMI networks

Muhammad Ismail, Mostafa Shahin, Mostafa F. Shaaban, Erchin Serpedin, Khalid Qaraqe

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

3 Citations (Scopus)

Abstract

Advanced metering infrastructure (AMI) networks are vulnerable against electricity theft cyber attacks. Different from the existing research that exploits shallow machine learning architectures for electricity theft detection, this paper proposes a deep neural network (DNN)-based customer-specific detector that can efficiently thwart such cyber attacks. The proposed DNN-based detector implements a sequential grid search analysis in its learning stage to appropriately fine tune its hyper-parameters, hence, improving the detection performance. Extensive test studies are carried out based on publicly available real energy consumption data of 5000 customers and the detector's performance is investigated against a mixture of different types of electricity theft cyber attacks. Simulation results demonstrate a significant performance improvement compared with state-of-the-art shallow detectors.

Original languageEnglish
Title of host publication2018 IEEE Wireless Communications and Networking Conference, WCNC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-6
Number of pages6
Volume2018-April
ISBN (Electronic)9781538617342
DOIs
Publication statusPublished - 8 Jun 2018
Event2018 IEEE Wireless Communications and Networking Conference, WCNC 2018 - Barcelona, Spain
Duration: 15 Apr 201818 Apr 2018

Other

Other2018 IEEE Wireless Communications and Networking Conference, WCNC 2018
CountrySpain
CityBarcelona
Period15/4/1818/4/18

Fingerprint

Advanced metering infrastructures
Electricity
Detectors
Learning systems
Energy utilization

Keywords

  • AMI networks
  • Cyber attacks
  • Deep machine learning
  • Electricity theft detection

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Ismail, M., Shahin, M., Shaaban, M. F., Serpedin, E., & Qaraqe, K. (2018). Efficient detection of electricity theft cyber attacks in AMI networks. In 2018 IEEE Wireless Communications and Networking Conference, WCNC 2018 (Vol. 2018-April, pp. 1-6). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WCNC.2018.8377010

Efficient detection of electricity theft cyber attacks in AMI networks. / Ismail, Muhammad; Shahin, Mostafa; Shaaban, Mostafa F.; Serpedin, Erchin; Qaraqe, Khalid.

2018 IEEE Wireless Communications and Networking Conference, WCNC 2018. Vol. 2018-April Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-6.

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

Ismail, M, Shahin, M, Shaaban, MF, Serpedin, E & Qaraqe, K 2018, Efficient detection of electricity theft cyber attacks in AMI networks. in 2018 IEEE Wireless Communications and Networking Conference, WCNC 2018. vol. 2018-April, Institute of Electrical and Electronics Engineers Inc., pp. 1-6, 2018 IEEE Wireless Communications and Networking Conference, WCNC 2018, Barcelona, Spain, 15/4/18. https://doi.org/10.1109/WCNC.2018.8377010
Ismail M, Shahin M, Shaaban MF, Serpedin E, Qaraqe K. Efficient detection of electricity theft cyber attacks in AMI networks. In 2018 IEEE Wireless Communications and Networking Conference, WCNC 2018. Vol. 2018-April. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-6 https://doi.org/10.1109/WCNC.2018.8377010
Ismail, Muhammad ; Shahin, Mostafa ; Shaaban, Mostafa F. ; Serpedin, Erchin ; Qaraqe, Khalid. / Efficient detection of electricity theft cyber attacks in AMI networks. 2018 IEEE Wireless Communications and Networking Conference, WCNC 2018. Vol. 2018-April Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-6
@inproceedings{44228f0604ff41b6a6929d1e02a4f8cf,
title = "Efficient detection of electricity theft cyber attacks in AMI networks",
abstract = "Advanced metering infrastructure (AMI) networks are vulnerable against electricity theft cyber attacks. Different from the existing research that exploits shallow machine learning architectures for electricity theft detection, this paper proposes a deep neural network (DNN)-based customer-specific detector that can efficiently thwart such cyber attacks. The proposed DNN-based detector implements a sequential grid search analysis in its learning stage to appropriately fine tune its hyper-parameters, hence, improving the detection performance. Extensive test studies are carried out based on publicly available real energy consumption data of 5000 customers and the detector's performance is investigated against a mixture of different types of electricity theft cyber attacks. Simulation results demonstrate a significant performance improvement compared with state-of-the-art shallow detectors.",
keywords = "AMI networks, Cyber attacks, Deep machine learning, Electricity theft detection",
author = "Muhammad Ismail and Mostafa Shahin and Shaaban, {Mostafa F.} and Erchin Serpedin and Khalid Qaraqe",
year = "2018",
month = "6",
day = "8",
doi = "10.1109/WCNC.2018.8377010",
language = "English",
volume = "2018-April",
pages = "1--6",
booktitle = "2018 IEEE Wireless Communications and Networking Conference, WCNC 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Efficient detection of electricity theft cyber attacks in AMI networks

AU - Ismail, Muhammad

AU - Shahin, Mostafa

AU - Shaaban, Mostafa F.

AU - Serpedin, Erchin

AU - Qaraqe, Khalid

PY - 2018/6/8

Y1 - 2018/6/8

N2 - Advanced metering infrastructure (AMI) networks are vulnerable against electricity theft cyber attacks. Different from the existing research that exploits shallow machine learning architectures for electricity theft detection, this paper proposes a deep neural network (DNN)-based customer-specific detector that can efficiently thwart such cyber attacks. The proposed DNN-based detector implements a sequential grid search analysis in its learning stage to appropriately fine tune its hyper-parameters, hence, improving the detection performance. Extensive test studies are carried out based on publicly available real energy consumption data of 5000 customers and the detector's performance is investigated against a mixture of different types of electricity theft cyber attacks. Simulation results demonstrate a significant performance improvement compared with state-of-the-art shallow detectors.

AB - Advanced metering infrastructure (AMI) networks are vulnerable against electricity theft cyber attacks. Different from the existing research that exploits shallow machine learning architectures for electricity theft detection, this paper proposes a deep neural network (DNN)-based customer-specific detector that can efficiently thwart such cyber attacks. The proposed DNN-based detector implements a sequential grid search analysis in its learning stage to appropriately fine tune its hyper-parameters, hence, improving the detection performance. Extensive test studies are carried out based on publicly available real energy consumption data of 5000 customers and the detector's performance is investigated against a mixture of different types of electricity theft cyber attacks. Simulation results demonstrate a significant performance improvement compared with state-of-the-art shallow detectors.

KW - AMI networks

KW - Cyber attacks

KW - Deep machine learning

KW - Electricity theft detection

UR - http://www.scopus.com/inward/record.url?scp=85049171040&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049171040&partnerID=8YFLogxK

U2 - 10.1109/WCNC.2018.8377010

DO - 10.1109/WCNC.2018.8377010

M3 - Conference contribution

VL - 2018-April

SP - 1

EP - 6

BT - 2018 IEEE Wireless Communications and Networking Conference, WCNC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -