A CGAN-based adversarial attack method for data-driven state estimation

With the development of data science and technology, the data-driven algorithms under the new power system architecture provide support for real-time and accurate state estimation (SE). However, the adoption of data-driven algorithms also introduces new security risks to power systems due to their i...

Full description

Saved in:
Bibliographic Details
Main Authors: Qi Wang, Jing Zhang, Jianxiong Hu, Shutan Wu, Shiyi Hou, Yi Tang
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:International Journal of Electrical Power & Energy Systems
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0142061525004260
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849768498035687424
author Qi Wang
Jing Zhang
Jianxiong Hu
Shutan Wu
Shiyi Hou
Yi Tang
author_facet Qi Wang
Jing Zhang
Jianxiong Hu
Shutan Wu
Shiyi Hou
Yi Tang
author_sort Qi Wang
collection DOAJ
description With the development of data science and technology, the data-driven algorithms under the new power system architecture provide support for real-time and accurate state estimation (SE). However, the adoption of data-driven algorithms also introduces new security risks to power systems due to their inherent limitations, such as lack of interpretability and poor robustness. Their sensitivity to small perturbations and the limitation of generalization ability make them vulnerable to adversarial attacks. Therefore, to reveal the security threats of adversarial attacks, a conditional generative adversarial network (CGAN) is innovatively adapted to the attack vector generation scenario of the power system in this paper. The feature decoupling and parameter-guided generation capabilities of the model are leveraged to produce adversarial samples that are both covert and threatening. In the proposed CGAN-based adversarial attack method, attackers can execute effective attacks by accessing grid measurements, without requiring any prior knowledge or deep understanding of the system. Simulation results demonstrate that the proposed method could compromise the state estimation process while evading bad data detection, all with reduced attack costs. This enables attackers to manipulate the output of the state estimation model according to their intentions, which represents an improvement over previous work. Comparative analysis with other traditional adversarial attack methods further indicates its effectiveness, thereby uncovering critical security vulnerabilities in data-driven state estimation algorithms.
format Article
id doaj-art-d06c8e96e71245bdad3b9d8d176da444
institution DOAJ
issn 0142-0615
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series International Journal of Electrical Power & Energy Systems
spelling doaj-art-d06c8e96e71245bdad3b9d8d176da4442025-08-20T03:03:46ZengElsevierInternational Journal of Electrical Power & Energy Systems0142-06152025-09-0117011087810.1016/j.ijepes.2025.110878A CGAN-based adversarial attack method for data-driven state estimationQi Wang0Jing Zhang1Jianxiong Hu2Shutan Wu3Shiyi Hou4Yi Tang5Corresponding author at: School of Electrical Engineering, Southeast University, Nanjing 210096, China.; School of Electrical Engineering, Southeast University, Nanjing 210000, ChinaSchool of Electrical Engineering, Southeast University, Nanjing 210000, ChinaSchool of Electrical Engineering, Southeast University, Nanjing 210000, ChinaSchool of Electrical Engineering, Southeast University, Nanjing 210000, ChinaSchool of Electrical Engineering, Southeast University, Nanjing 210000, ChinaSchool of Electrical Engineering, Southeast University, Nanjing 210000, ChinaWith the development of data science and technology, the data-driven algorithms under the new power system architecture provide support for real-time and accurate state estimation (SE). However, the adoption of data-driven algorithms also introduces new security risks to power systems due to their inherent limitations, such as lack of interpretability and poor robustness. Their sensitivity to small perturbations and the limitation of generalization ability make them vulnerable to adversarial attacks. Therefore, to reveal the security threats of adversarial attacks, a conditional generative adversarial network (CGAN) is innovatively adapted to the attack vector generation scenario of the power system in this paper. The feature decoupling and parameter-guided generation capabilities of the model are leveraged to produce adversarial samples that are both covert and threatening. In the proposed CGAN-based adversarial attack method, attackers can execute effective attacks by accessing grid measurements, without requiring any prior knowledge or deep understanding of the system. Simulation results demonstrate that the proposed method could compromise the state estimation process while evading bad data detection, all with reduced attack costs. This enables attackers to manipulate the output of the state estimation model according to their intentions, which represents an improvement over previous work. Comparative analysis with other traditional adversarial attack methods further indicates its effectiveness, thereby uncovering critical security vulnerabilities in data-driven state estimation algorithms.http://www.sciencedirect.com/science/article/pii/S0142061525004260Adversarial attacksConditional generative adversarial networksData-driven algorithmsGenerative adversarial networksState estimation
spellingShingle Qi Wang
Jing Zhang
Jianxiong Hu
Shutan Wu
Shiyi Hou
Yi Tang
A CGAN-based adversarial attack method for data-driven state estimation
International Journal of Electrical Power & Energy Systems
Adversarial attacks
Conditional generative adversarial networks
Data-driven algorithms
Generative adversarial networks
State estimation
title A CGAN-based adversarial attack method for data-driven state estimation
title_full A CGAN-based adversarial attack method for data-driven state estimation
title_fullStr A CGAN-based adversarial attack method for data-driven state estimation
title_full_unstemmed A CGAN-based adversarial attack method for data-driven state estimation
title_short A CGAN-based adversarial attack method for data-driven state estimation
title_sort cgan based adversarial attack method for data driven state estimation
topic Adversarial attacks
Conditional generative adversarial networks
Data-driven algorithms
Generative adversarial networks
State estimation
url http://www.sciencedirect.com/science/article/pii/S0142061525004260
work_keys_str_mv AT qiwang acganbasedadversarialattackmethodfordatadrivenstateestimation
AT jingzhang acganbasedadversarialattackmethodfordatadrivenstateestimation
AT jianxionghu acganbasedadversarialattackmethodfordatadrivenstateestimation
AT shutanwu acganbasedadversarialattackmethodfordatadrivenstateestimation
AT shiyihou acganbasedadversarialattackmethodfordatadrivenstateestimation
AT yitang acganbasedadversarialattackmethodfordatadrivenstateestimation
AT qiwang cganbasedadversarialattackmethodfordatadrivenstateestimation
AT jingzhang cganbasedadversarialattackmethodfordatadrivenstateestimation
AT jianxionghu cganbasedadversarialattackmethodfordatadrivenstateestimation
AT shutanwu cganbasedadversarialattackmethodfordatadrivenstateestimation
AT shiyihou cganbasedadversarialattackmethodfordatadrivenstateestimation
AT yitang cganbasedadversarialattackmethodfordatadrivenstateestimation