How effective are synthetic attack models to detect real-world energy theft?

<p>Advanced Metering Infrastructure plays a significant role in smart grid systems by enabling efficient two-way communication between energy suppliers and consumers. Despite its benefits, AMI faces numerous security challenges, including vulnerabilities to cyberattacks and non-technical losse...

Full description

Saved in:
Bibliographic Details
Main Author: Emran Altamimi (21397883) (author)
Other Authors: Abdulaziz Al-Ali (16393288) (author), Abdulla K. Al-Ali (22928911) (author), Hussein Aly (18877555) (author), Qutaibah M. Malluhi (14151912) (author)
Published: 2025
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513525492219904
author Emran Altamimi (21397883)
author2 Abdulaziz Al-Ali (16393288)
Abdulla K. Al-Ali (22928911)
Hussein Aly (18877555)
Qutaibah M. Malluhi (14151912)
author2_role author
author
author
author
author_facet Emran Altamimi (21397883)
Abdulaziz Al-Ali (16393288)
Abdulla K. Al-Ali (22928911)
Hussein Aly (18877555)
Qutaibah M. Malluhi (14151912)
author_role author
dc.creator.none.fl_str_mv Emran Altamimi (21397883)
Abdulaziz Al-Ali (16393288)
Abdulla K. Al-Ali (22928911)
Hussein Aly (18877555)
Qutaibah M. Malluhi (14151912)
dc.date.none.fl_str_mv 2025-08-21T12:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.energy.2025.137763
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/How_effective_are_synthetic_attack_models_to_detect_real-world_energy_theft_/30971680
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Electronics, sensors and digital hardware
Information and computing sciences
Cybersecurity and privacy
Data management and data science
Machine learning
Energy theft
Non-technical loss
Attack models
Smart grid
Machine learning
dc.title.none.fl_str_mv How effective are synthetic attack models to detect real-world energy theft?
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>Advanced Metering Infrastructure plays a significant role in smart grid systems by enabling efficient two-way communication between energy suppliers and consumers. Despite its benefits, AMI faces numerous security challenges, including vulnerabilities to cyberattacks and non-technical losses, potentially leading to substantial revenue losses. Data-driven approaches to electricity fraud detection have gained popularity due to smart grids’ big data. However, available datasets lack annotated real anomalies, which poses significant challenges in developing effective detection systems. As a response, researchers have developed synthetic attack models to simulate real-world theft. In this paper, we analyze the validity of popular synthetic attack models and their limitations in representing real-world theft scenarios. By conducting an empirical evaluation of synthetic attacks, we provide a practical assessment of their efficacy and their correlation with one another. Our findings suggest that while these models perform well when tested on synthetic attacks, their performance considerably deteriorates on real-world theft, considering the only real-world public dataset. Furthermore, some attack model pairs were found to be more correlated than others. Consequently, this paper suggests a sufficient subset of synthetic attacks for training and testing to effectively capture the full set of synthetic attacks.</p><h2>Other Information</h2> <p> Published in: Energy<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.energy.2025.137763" target="_blank">https://dx.doi.org/10.1016/j.energy.2025.137763</a></p>
eu_rights_str_mv openAccess
id Manara2_6e76cca3a10e0f6547ac46c6e6a574f1
identifier_str_mv 10.1016/j.energy.2025.137763
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/30971680
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling How effective are synthetic attack models to detect real-world energy theft?Emran Altamimi (21397883)Abdulaziz Al-Ali (16393288)Abdulla K. Al-Ali (22928911)Hussein Aly (18877555)Qutaibah M. Malluhi (14151912)EngineeringElectronics, sensors and digital hardwareInformation and computing sciencesCybersecurity and privacyData management and data scienceMachine learningEnergy theftNon-technical lossAttack modelsSmart gridMachine learning<p>Advanced Metering Infrastructure plays a significant role in smart grid systems by enabling efficient two-way communication between energy suppliers and consumers. Despite its benefits, AMI faces numerous security challenges, including vulnerabilities to cyberattacks and non-technical losses, potentially leading to substantial revenue losses. Data-driven approaches to electricity fraud detection have gained popularity due to smart grids’ big data. However, available datasets lack annotated real anomalies, which poses significant challenges in developing effective detection systems. As a response, researchers have developed synthetic attack models to simulate real-world theft. In this paper, we analyze the validity of popular synthetic attack models and their limitations in representing real-world theft scenarios. By conducting an empirical evaluation of synthetic attacks, we provide a practical assessment of their efficacy and their correlation with one another. Our findings suggest that while these models perform well when tested on synthetic attacks, their performance considerably deteriorates on real-world theft, considering the only real-world public dataset. Furthermore, some attack model pairs were found to be more correlated than others. Consequently, this paper suggests a sufficient subset of synthetic attacks for training and testing to effectively capture the full set of synthetic attacks.</p><h2>Other Information</h2> <p> Published in: Energy<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.energy.2025.137763" target="_blank">https://dx.doi.org/10.1016/j.energy.2025.137763</a></p>2025-08-21T12:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.energy.2025.137763https://figshare.com/articles/journal_contribution/How_effective_are_synthetic_attack_models_to_detect_real-world_energy_theft_/30971680CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/309716802025-08-21T12:00:00Z
spellingShingle How effective are synthetic attack models to detect real-world energy theft?
Emran Altamimi (21397883)
Engineering
Electronics, sensors and digital hardware
Information and computing sciences
Cybersecurity and privacy
Data management and data science
Machine learning
Energy theft
Non-technical loss
Attack models
Smart grid
Machine learning
status_str publishedVersion
title How effective are synthetic attack models to detect real-world energy theft?
title_full How effective are synthetic attack models to detect real-world energy theft?
title_fullStr How effective are synthetic attack models to detect real-world energy theft?
title_full_unstemmed How effective are synthetic attack models to detect real-world energy theft?
title_short How effective are synthetic attack models to detect real-world energy theft?
title_sort How effective are synthetic attack models to detect real-world energy theft?
topic Engineering
Electronics, sensors and digital hardware
Information and computing sciences
Cybersecurity and privacy
Data management and data science
Machine learning
Energy theft
Non-technical loss
Attack models
Smart grid
Machine learning