Deep Autoencoder-based Detection of Electricity Stealth Cyberattacks in AMI Networks

Abdulrahman Takiddin, Muhammad Ismail, Usman Zafar, Erchin Serpedin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

12 Citations (Scopus)

Abstract

Efficient recognition of electricity stealth cyberattacks within the advanced metering infrastructures (AMIs) is limited by the lack of deliberate electricity theft datasets. Thus, anomaly-based detectors trained using only the information provided by the electricity usage profiles of truthful customers can overcome this limitation. This paper investigates the performance of deep (stacked) basic autoencoders (BAEs) with fully connected (FC) and long-short-Term-memory (LSTM) structures for electricity thefts identification. The performance of the BAEs is compared to existing anomaly detectors such as one-class support vector machine (SVM) and auto-regressive integrated moving average (ARIMA) models as benchmarks. This study shows an enhancement of 8-9% in true positive rate and 7-16% in false positive rate for the deep LSTM-based BAE architecture relative to the benchmark anomaly detectors.

Original languageEnglish
Title of host publicationISSCS 2021 - International Symposium on Signals, Circuits and Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665449427
DOIs
Publication statusPublished - 15 Jul 2021
Event15th International Symposium on Signals, Circuits and Systems, ISSCS 2021 - Iasi, Romania
Duration: 15 Jul 202116 Jul 2021

Publication series

NameISSCS 2021 - International Symposium on Signals, Circuits and Systems

Conference

Conference15th International Symposium on Signals, Circuits and Systems, ISSCS 2021
Country/TerritoryRomania
CityIasi
Period15/07/2116/07/21

Keywords

  • autoencoders
  • deep learning
  • electricity theft

Fingerprint

Dive into the research topics of 'Deep Autoencoder-based Detection of Electricity Stealth Cyberattacks in AMI Networks'. Together they form a unique fingerprint.

Cite this