Defense Methods for Adversarial Attacks Against Power CPS Data-Driven Algorithms

The integration of large-scale power electronic devices has introduced a large number of strong nonlinear measurement/control nodes into the system, gradually transforming the traditional power system into a cyber physical system (CPS). Many system problems that were originally solved by model-drive...

Full description

Saved in:
Bibliographic Details
Main Authors: Weiping ZHU, Yi TANG, Xingshen WEI, Zengji LIU
Format: Article
Language:zho
Published: State Grid Energy Research Institute 2024-09-01
Series:Zhongguo dianli
Subjects:
Online Access:https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202312067
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850037940875427840
author Weiping ZHU
Yi TANG
Xingshen WEI
Zengji LIU
author_facet Weiping ZHU
Yi TANG
Xingshen WEI
Zengji LIU
author_sort Weiping ZHU
collection DOAJ
description The integration of large-scale power electronic devices has introduced a large number of strong nonlinear measurement/control nodes into the system, gradually transforming the traditional power system into a cyber physical system (CPS). Many system problems that were originally solved by model-driven methods have had to be analyzed using data-driven algorithms due to limitations such as dimensional disasters. However, the inherent flaws of data-driven algorithms introduce new risks to the safe and stable operation of the system, which attackers can exploit to launch adversarial attacks that may cause system power outages and even instability. In response to the potential adversarial attacks on data-driven algorithms in power CPS, this paper proposes corresponding defense methods from such three aspects as abnormal data filtering and recovery, algorithm vulnerability mining and optimization, and algorithm self interpretability improvement: abnormal data filter, GAN-based vulnerability mining and optimization method, data knowledge fusion model and its training method. The effectiveness of the proposed method is verified through case analysis.
format Article
id doaj-art-b2e342a776844af4a0bc0af80ac31a22
institution DOAJ
issn 1004-9649
language zho
publishDate 2024-09-01
publisher State Grid Energy Research Institute
record_format Article
series Zhongguo dianli
spelling doaj-art-b2e342a776844af4a0bc0af80ac31a222025-08-20T02:56:44ZzhoState Grid Energy Research InstituteZhongguo dianli1004-96492024-09-01579324310.11930/j.issn.1004-9649.202312067zgdl-57-08-zhuweipingDefense Methods for Adversarial Attacks Against Power CPS Data-Driven AlgorithmsWeiping ZHU0Yi TANG1Xingshen WEI2Zengji LIU3State Grid Jiangsu Electric Power Co., Ltd., Nanjing 210024, ChinaSchool of Electrical Engineering, Southeast University, Nanjing 211189, ChinaNARI Group Corporation (State Grid Electric Power Research Institute), Nanjing 211106, ChinaSchool of Electrical Engineering, Southeast University, Nanjing 211189, ChinaThe integration of large-scale power electronic devices has introduced a large number of strong nonlinear measurement/control nodes into the system, gradually transforming the traditional power system into a cyber physical system (CPS). Many system problems that were originally solved by model-driven methods have had to be analyzed using data-driven algorithms due to limitations such as dimensional disasters. However, the inherent flaws of data-driven algorithms introduce new risks to the safe and stable operation of the system, which attackers can exploit to launch adversarial attacks that may cause system power outages and even instability. In response to the potential adversarial attacks on data-driven algorithms in power CPS, this paper proposes corresponding defense methods from such three aspects as abnormal data filtering and recovery, algorithm vulnerability mining and optimization, and algorithm self interpretability improvement: abnormal data filter, GAN-based vulnerability mining and optimization method, data knowledge fusion model and its training method. The effectiveness of the proposed method is verified through case analysis.https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202312067adversarial attacksdata-driven algorithmspower cpsattack defense
spellingShingle Weiping ZHU
Yi TANG
Xingshen WEI
Zengji LIU
Defense Methods for Adversarial Attacks Against Power CPS Data-Driven Algorithms
Zhongguo dianli
adversarial attacks
data-driven algorithms
power cps
attack defense
title Defense Methods for Adversarial Attacks Against Power CPS Data-Driven Algorithms
title_full Defense Methods for Adversarial Attacks Against Power CPS Data-Driven Algorithms
title_fullStr Defense Methods for Adversarial Attacks Against Power CPS Data-Driven Algorithms
title_full_unstemmed Defense Methods for Adversarial Attacks Against Power CPS Data-Driven Algorithms
title_short Defense Methods for Adversarial Attacks Against Power CPS Data-Driven Algorithms
title_sort defense methods for adversarial attacks against power cps data driven algorithms
topic adversarial attacks
data-driven algorithms
power cps
attack defense
url https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202312067
work_keys_str_mv AT weipingzhu defensemethodsforadversarialattacksagainstpowercpsdatadrivenalgorithms
AT yitang defensemethodsforadversarialattacksagainstpowercpsdatadrivenalgorithms
AT xingshenwei defensemethodsforadversarialattacksagainstpowercpsdatadrivenalgorithms
AT zengjiliu defensemethodsforadversarialattacksagainstpowercpsdatadrivenalgorithms