Localization of Coordinated Cyber-Physical Attacks in Power Grids Using Moving Target Defense and Deep Learning

Chen, Yexiang; Lakshminarayana, Subhash; Teng, Fei

doi:10.1109/smartgridcomm52983.2022.9960982

Cited by 5 publications

(14 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where a = −∆Hθ p is a simplest FDIA that can mask the effect of the physical attack. Actually, the stealthy CCPA (SCCPA) in Formula ( 8) is called the optimized CCPA [4], also termed as the "partial CCPA" [17]. Nevertheless, there is also one type of stealthy CCPA.…”

Section: Ccpamentioning

confidence: 99%

“…Actually, the problem of FDIAs localization has become a hot spot [13][14][15][16]; however, the number of similar studies focused on CCPAs is only one [17]. Essentially, the problem of attack localization is a nonlinear multiple classifications problem.…”

Section: Introductionmentioning

confidence: 99%

“…Specifically, the problem of CCPA localization is to identify the disconnected lines in the CCPA. After carefully taking the study in the literature [17] into account, we point to two main reasons for this situation. One is that the total number of classifications is not easy to determine.…”

Section: Introductionmentioning

confidence: 99%

“…Effectively, the data are the compromised measurements. In [17], a measurement formula was proposed as follows:…”

Section: Introductionmentioning

confidence: 99%

“…For simplicity, the implication of each quantity in Formula (1) may be seen in [17]. The representation of Formula (1) is complex, which increases the difficulty of calculation.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Localization of Coordinated Cyber-Physical Attacks in Power Grids Using Moving Target Defense and Machine Learning

Yu,

Li,

2024

Electronics

View full text Add to dashboard Cite

Coordinated cyber-physical attacks (CCPAs) are dangerously stealthy and have considerable destructive effects against power grids. The problem of stealthy CCPA (SCCPA) localization, specifically identifying disconnected lines in attack, is a nonlinear multi-classification problem. To the best of our knowledge, only one paper has studied the problem; nevertheless, the total number of classifications is not appropriate. In the paper, we propose several methods to solve the problem of SCCPA localization. Firstly, considering the practical constraints and abiding by one of our previous studies, we elaborately determine the total number of classifications and design an approach for generating training and testing datasets. Secondly, we develop two algorithms to solve multiple classifications via the support vector machine (SVM) and random forest (RF), respectively. Similarly, we also present a one-dimensional convolutional neural network (1D-CNN) architecture. Finally, extensive simulations are carried out for IEEE 14-bus, 30-bus, and 118-bus power system, respectively, and we verify the effectiveness of our approaches in solving the problem of SCCPA localization.

show abstract

Section: Ccpamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Effectively, the data are the compromised measurements. In [17], a measurement formula was proposed as follows:…”

Section: Introductionmentioning

confidence: 99%

“…For simplicity, the implication of each quantity in Formula (1) may be seen in [17]. The representation of Formula (1) is complex, which increases the difficulty of calculation.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations