Multi-View Convolutional Neural Network for Data Spoofing Cyber-Attack Detection in Distribution Synchrophasors

Qiu, Wei; Tang, Qiu; Wang, Yajun; Zhan, Lingwei; Liu, Yilu; Yao, Wenxuan

doi:10.1109/tsg.2020.2971148

Title: Multi-View Convolutional Neural Network for Data Spoofing Cyber-Attack Detection in Distribution Synchrophasors

Full Record
Other Related Research

Abstract

Security of Distribution Synchrophasors Data (DSD) is of paramount importance as the data is used for critical smart grid applications including situational awareness, advanced protection, and dynamic control. Unfortunately, the DSD are attractive targets for malicious attackers aiming to damage grid. Data spoofing is a new class of deceiving attack, where the DSD of one Phasor Measurement Units (PMUs) is tampered by other PMUs thereby spoiling measurement based applications. In order to address this issue, a source authentication based data spoofing attack detection method is proposed using Multi-view Convolutional Neural Network (MCNN). First, common components embedded in raw frequency measurements from DSD are removed by Savitzky-Golay (SG) filter. Second, fast S transform (FST) is utilized to extract representative spatial fingerprints via time frequency analysis. Third, the spatial fingerprint is fed to MCNN, which combines dilated and standard convolutions for automatic feather extraction and source identification. Finally, according to the output of MCNN, spoofing attack detection is performed via threshold criterion. Extensive experiments with actual DSD from multiple locations in FNET/Grideye are conducted to verify the effectiveness of the proposed method.

Authors:

^[1];

^[2];

^[3];

^[2];

^[2]

Hunan Univ., Changsha (China)
Univ. of Tennessee, Knoxville, TN (United States)
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

Publication Date:: Mon Feb 03 00:00:00 EST 2020

Research Org.:: Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

Sponsoring Org.:: USDOE; National Science Foundation (NSF)

OSTI Identifier:: 1648880

Grant/Contract Number:: AC05-00OR22725; EEC-1041877

Resource Type:: Accepted Manuscript

Journal Name:: IEEE Transactions on Smart Grid

Additional Journal Information:: Journal Volume: 11; Journal Issue: 4; Journal ID: ISSN 1949-3053

Publisher:: IEEE

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING; data spoofing attack; distribution synchrophasors data; multi-view convolutional neural network; source authentication

Citation Formats


                    Qiu, Wei, Tang, Qiu, Wang, Yajun, Zhan, Lingwei, Liu, Yilu, and Yao, Wenxuan. Multi-View Convolutional Neural Network for Data Spoofing Cyber-Attack Detection in Distribution Synchrophasors.  United States: N. p., 2020. 
Web.  doi:10.1109/tsg.2020.2971148.

Copy to clipboard


                    Qiu, Wei, Tang, Qiu, Wang, Yajun, Zhan, Lingwei, Liu, Yilu, & Yao, Wenxuan. Multi-View Convolutional Neural Network for Data Spoofing Cyber-Attack Detection in Distribution Synchrophasors.  United States.  https://doi.org/10.1109/tsg.2020.2971148

Copy to clipboard


                    Qiu, Wei, Tang, Qiu, Wang, Yajun, Zhan, Lingwei, Liu, Yilu, and Yao, Wenxuan. Mon .  
"Multi-View Convolutional Neural Network for Data Spoofing Cyber-Attack Detection in Distribution Synchrophasors".  United States.  https://doi.org/10.1109/tsg.2020.2971148.  https://www.osti.gov/servlets/purl/1648880.

Copy to clipboard


                    
@article{osti_1648880,

  title        = {Multi-View Convolutional Neural Network for Data Spoofing Cyber-Attack Detection in Distribution Synchrophasors},

  author       = {Qiu, Wei and Tang, Qiu and Wang, Yajun and Zhan, Lingwei and Liu, Yilu and Yao, Wenxuan},

  abstractNote = {Security of Distribution Synchrophasors Data (DSD) is of paramount importance as the data is used for critical smart grid applications including situational awareness, advanced protection, and dynamic control. Unfortunately, the DSD are attractive targets for malicious attackers aiming to damage grid. Data spoofing is a new class of deceiving attack, where the DSD of one Phasor Measurement Units (PMUs) is tampered by other PMUs thereby spoiling measurement based applications. In order to address this issue, a source authentication based data spoofing attack detection method is proposed using Multi-view Convolutional Neural Network (MCNN). First, common components embedded in raw frequency measurements from DSD are removed by Savitzky-Golay (SG) filter. Second, fast S transform (FST) is utilized to extract representative spatial fingerprints via time frequency analysis. Third, the spatial fingerprint is fed to MCNN, which combines dilated and standard convolutions for automatic feather extraction and source identification. Finally, according to the output of MCNN, spoofing attack detection is performed via threshold criterion. Extensive experiments with actual DSD from multiple locations in FNET/Grideye are conducted to verify the effectiveness of the proposed method.},

  doi          = {10.1109/tsg.2020.2971148},

  journal      = {IEEE Transactions on Smart Grid},

  number       = 4,

  volume       = 11,

  place        = {United States},

  year         = {Mon Feb 03 00:00:00 EST 2020},

  month        = {Mon Feb 03 00:00:00 EST 2020}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1109/tsg.2020.2971148

Other availability

Search WorldCat to find libraries that may hold this journal

Citation Metrics:

Cited by: 19 works

Citation information provided by
Web of Science

Save / Share:

Export Metadata

Save to My Library

Similar Records in DOE PAGES and OSTI.GOV collections:

Detection of Synchrophasor False Data Injection Attack using Feature Interactive Network

Journal Article Qiu, Wei ; Tang, Qiu ; Zhu, Kunzhi ; ... - IEEE Transactions on Smart Grid

The synchrophasor data recorded by Phasor Measurement Units (PMUs) plays an increasingly critical role in the regulation and situational awareness of power systems. However, the widely installed PMUs are vulnerable to multiple malicious attacks from cyber hackers during data transmission and storage. To address this problem, a Modified Ensemble Empirical Mode Decomposition (MEEMD) is proposed first to extract the intrinsic mode functions of each Synchrophasor Data Attacks (SDA). The frequency-based adaptive screening criterion embedded in MEEMD is used to eliminate the false intrinsic mode functions. Next, a Multivariate Convolutional Neural Network (MCNN) is proposed to identify multiple SDA by utilizingmore »« less
https://doi.org/10.1109/tsg.2020.3014311

Full Text Available
Synchrophasor Data Correction under GPS Spoofing Attack: A State Estimation-Based Approach

Journal Article Fan, Xiaoyuan ; Du, Liang ; Duan, Dongliang - IEEE Transactions on Smart Grid

GPS spoofing attack (GSA) has been shown to be one of the most imminent threats to almost all cyber-physical systems incorporated with the civilian GPS signal. Specifically, for our current agenda of the modernization of the power grid, this may greatly jeopardize the benefits provided by the pervasively installed phasor measurement units (PMU). In this paper, we consider the case where synchrophasor data from PMUs are compromised due to the presence of a single GSA, and show that it can be corrected by signal processing techniques. In particular, we introduce a statistical model for synchrophasorbased power system state estimation (SE),more »« less
https://doi.org/10.1109/TSG.2017.2662688
Synchrophasor Data Correction under GPS Spoofing Attack: A State Estimation Based Approach

Journal Article Fan, Xiaoyuan ; Du, Liang ; Duan, Dongliang - IEEE Transactions on Smart Grid

GPS spoofing attack (GSA) has been shown to be one of the most imminent threats to almost all cyber-physical systems incorporated with the civilian GPS signal. Specifically, for our current agenda of the modernization of the power grid, this may greatly jeopardize the benefits provided by the pervasively installed phasor measurement units (PMU). In this study, we consider the case where synchrophasor data from PMUs are compromised due to the presence of a single GSA, and show that it can be corrected by signal processing techniques. In particular, we introduce a statistical model for synchrophasorbased power system state estimation (SE),more »« less
Cited by 65
https://doi.org/10.1109/TSG.2017.2662688

Full Text Available
Closed-Form Solution for Synchrophasor Data Correction under GPS Spoofing Attack

Conference Fan, Xiaoyuan ; Pal, Seemita ; Duan, Dongliang ; ... - IEEE Power & Energy Society General Meeting (Online)

Phasor Measurement Units (PMUs) are increasingly being deployed to augment monitoring, protection and control applications in the power grid. PMUs rely on the Global Positioning System (GPS) for generation of time-synchronized and accurate measurements. However, civilian GPS signals, being unencrypted, are susceptible to GPS spoofing attacks (GSA). Hence ensuring the integrity of GPS-timing dependent synchrophasor data has become critical. In this paper, a closed-form analytical solution for estimating the GSA phase shift has been proposed and integrated to the spoofing detection & correction framework. Extensive simulations have been performed in order to verify the accuracy of the solution in determiningmore »« less
https://doi.org/10.1109/PESGM.2018.8586177
Spatio-Temporal Characterization of Synchrophasor Data Against Spoofing Attacks in Smart Grids

Journal Article Cui, Yi ; Bai, Feifei ; Liu, Yilu ; ... - IEEE Transactions on Smart Grid

“Source ID Mix” has emerged as a new type of highly deceiving attack which can alter the source information of synchrophasor data measured by multiple phasor measurement units, thereby paralyzing many wide-area measurement systems applications. To address such sophisticated cyber attacks, we have exploited the spatio-temporal characteristics of synchrophasor data for authenticating measurements’ source information. Specifically, the source authentication is performed when the measurements are subjected to three types of spoofing attacks. Some practical difficulties in applying the proposed method on real-time authentication caused by insufficient measurement data have also been solved. Experimental results with real synchrophasor measurements have validatedmore »« less
Cited by 21
https://doi.org/10.1109/TSG.2019.2891852

Full Text Available

Similar Records