Spatio-temporal Graph-Based Generation and Detection of Adversarial False Data Injection Evasion Attacks in Smart Grids

Smart power grids are vulnerable to security threats due to their cyber-physical nature. Existing data-driven detectors aim to address simple traditional false data injection attacks (FDIAs). However, adversarial false data injection evasion attacks (FDIEAs) present a more serious threat as adversar...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on artificial intelligence Ročník 5; číslo 12; s. 6601 - 6616
Hlavní autori:	Takiddin, Abdulrahman, Ismail, Muhammad, Atat, Rachad, Serpedin, Erchin
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	IEEE 01.12.2024
Predmet:	Accuracy Artificial intelligence Cyber-physical systems security cyberattacks Detectors evasion attacks false data injection attacks (FDIAs) graph autoencoder graph neural networks (GNNs) machine learning Robustness Smart grids Topology Training
ISSN:	2691-4581, 2691-4581
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Smart power grids are vulnerable to security threats due to their cyber-physical nature. Existing data-driven detectors aim to address simple traditional false data injection attacks (FDIAs). However, adversarial false data injection evasion attacks (FDIEAs) present a more serious threat as adversaries, with different levels of knowledge about the system, inject adversarial samples to circumvent the grid's attack detection system. The robustness of state-of-the-art graph-based detectors has not been investigated against sophisticated FDIEAs. Hence, this article answers three research questions. 1) What is the impact of utilizing spatio-temporal features to craft adversarial samples and how to select attack nodes? 2) How can adversaries generate surrogate spatio-temporal data when they lack knowledge about the system topology? 3) What are the required model characteristics for a robust detection against adversarial FDIEAs? To answer the questions, we examine the robustness of several detectors against five attack cases and conclude the following: 1) Attack generation with full knowledge using spatio-temporal features leads to 5%-26% and 2%-5% higher degradation in detection rate (DR) compared to traditional FDIAs and using temporal features, respectively, whereas centrality analysis-based attack node selection leads to 3%-11% higher degradation in DR compared to a random selection; 2) Stochastic geometry-based graph generation to create surrogate adversarial topologies and samples leads to 3%-13% higher degradation in DR compared to traditional FDIAs; and 3) Adopting an unsupervised spatio-temporal graph autoencoder (STGAE)-based detector enhances the DR by 5<inline-formula><tex-math notation="LaTeX">-</tex-math></inline-formula>53% compared to benchmark detectors against FDIEAs.
AbstractList	Smart power grids are vulnerable to security threats due to their cyber-physical nature. Existing data-driven detectors aim to address simple traditional false data injection attacks (FDIAs). However, adversarial false data injection evasion attacks (FDIEAs) present a more serious threat as adversaries, with different levels of knowledge about the system, inject adversarial samples to circumvent the grid's attack detection system. The robustness of state-of-the-art graph-based detectors has not been investigated against sophisticated FDIEAs. Hence, this article answers three research questions. 1) What is the impact of utilizing spatio-temporal features to craft adversarial samples and how to select attack nodes? 2) How can adversaries generate surrogate spatio-temporal data when they lack knowledge about the system topology? 3) What are the required model characteristics for a robust detection against adversarial FDIEAs? To answer the questions, we examine the robustness of several detectors against five attack cases and conclude the following: 1) Attack generation with full knowledge using spatio-temporal features leads to 5%-26% and 2%-5% higher degradation in detection rate (DR) compared to traditional FDIAs and using temporal features, respectively, whereas centrality analysis-based attack node selection leads to 3%-11% higher degradation in DR compared to a random selection; 2) Stochastic geometry-based graph generation to create surrogate adversarial topologies and samples leads to 3%-13% higher degradation in DR compared to traditional FDIAs; and 3) Adopting an unsupervised spatio-temporal graph autoencoder (STGAE)-based detector enhances the DR by 5<inline-formula><tex-math notation="LaTeX">-</tex-math></inline-formula>53% compared to benchmark detectors against FDIEAs.
Author	Ismail, Muhammad Atat, Rachad Takiddin, Abdulrahman Serpedin, Erchin
Author_xml	– sequence: 1 givenname: Abdulrahman orcidid: 0000-0003-4793-003X surname: Takiddin fullname: Takiddin, Abdulrahman email: a.takiddin@fsu.edu organization: Department of Electrical and Computer Engineering, FAMU-FSU College of Engineering, Florida State University, Tallahassee, FL, USA – sequence: 2 givenname: Muhammad orcidid: 0000-0002-8051-9747 surname: Ismail fullname: Ismail, Muhammad email: mismail@tntech.edu organization: Department of Computer Science, Tennessee Tech University, Cookeville, TN, USA – sequence: 3 givenname: Rachad orcidid: 0000-0001-8075-6243 surname: Atat fullname: Atat, Rachad email: rachad.atat@lau.edu.lb organization: Department of Computer Science and Mathematics, Lebanese American University, Beirut, Lebanon – sequence: 4 givenname: Erchin orcidid: 0000-0001-9069-770X surname: Serpedin fullname: Serpedin, Erchin email: eserpedin@tamu.edu organization: Department of Electrical and Computer Engineering, Texas A&M University, College Station, TX, USA
BookMark	eNpNkMtuwjAQRa2KSqWUfRdd-AdCPX4EZ5nyKhJSF9B1ZOyxGgpJZEdU_fsmhQWrmdHcM4_7SAZVXSEhz8AmACx73eXrCWdcToRMpQK4I0OeZpBIpWFwkz-QcYwHxhhXwDmfDsnPtjFtWSctnpo6mCNdBdN8JW8moqMrrDD07YqaytE5tmj_q9rT3J0xRBPKjlmaY0Q6N62h6-pw1SzOJvYxb1tjvyMtK7o9mdB2G0oXn8i976nxNY7I53Kxm70nm4_VepZvEguCt4kTzmvnUAruQCovOAjmM6bBg5_67gcFU416nymrJRqbKuuUBMvR71PjxIiwy1wb6hgD-qIJZXfGbwGs6L0rOu-K3rvi6l2HvFyQEhFv5KmWWgrxB421bZo
CODEN	ITAICB
Cites_doi	10.1109/TII.2022.3178418 10.1109/TPEL.2022.3206239 10.1109/TSP.2019.2955832 10.1109/GlobalSIP45357.2019.8969373 10.1109/CIT/IUCC/DASC/PICOM.2015.90 10.1109/ITNEC52019.2021.9587009 10.1109/TSG.2020.3010510 10.1109/AIPR50011.2020.9425190 10.1109/JSYST.2019.2927469 10.1109/TII.2023.3290942 10.1109/SP.2017.49 10.1109/TCYB.2021.3125345 10.1109/AIAM50918.2020.00033 10.1109/TPWRS.2021.3091616 10.1109/TPWRS.2016.2634318 10.1109/JSYST.2021.3136683 10.1109/JIOT.2022.3147040 10.1109/TSG.2016.2540439 10.1109/TSG.2020.3047864 10.1109/JIOT.2021.3113900 10.1109/JIOT.2020.2983911 10.1016/j.jisa.2019.02.008 10.1109/TETCI.2019.2902845 10.1109/TII.2021.3102332 10.1109/TSG.2022.3193989 10.1109/TSG.2021.3109628 10.1109/TSG.2019.2947148 10.1109/JSYST.2014.2341597 10.1109/TSG.2019.2949998 10.1103/PhysRevE.83.036106 10.1109/TPAS.1979.319407 10.1109/TNNLS.2023.3274538 10.1109/TAI.2023.3286831 10.1109/TAI.2021.3096489 10.1109/TSG.2010.2044814 10.1109/TPWRS.2010.2051168 10.23919/EUSIPCO55093.2022.9909779 10.2991/msam-17.2017.68 10.1109/TSG.2023.3261970 10.1109/TSG.2022.3204796 10.1109/JSYST.2021.3109082 10.1109/TII.2018.2825243 10.1109/TETCI.2022.3232821 10.1109/TII.2023.3281664 10.1007/978-0-387-30164-8 10.1007/978-3-319-33331-1_16 10.1109/CSCI.2017.1 10.1109/MITS.2014.2324023 10.1109/ACCESS.2023.3323617 10.1109/JSYST.2020.3030238 10.1109/JSYST.2022.3231897 10.1109/ACCESS.2019.2902910 10.1109/TAI.2021.3076021 10.1109/TII.2023.3331544 10.1145/3133956.3134057
ContentType	Journal Article
DBID	97E RIA RIE AAYXX CITATION
DOI	10.1109/TAI.2024.3464511
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef
DatabaseTitle	CrossRef
DatabaseTitleList
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Computer Science
EISSN	2691-4581
EndPage	6616
ExternalDocumentID	10_1109_TAI_2024_3464511 10684843
Genre	orig-research
GrantInformation_xml	– fundername: NSF EPCN grantid: 2220346; 2220347
GroupedDBID	0R~ 97E AASAJ AAWTH ABAZT ABJNI ABQJQ ABVLG AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS IEDLZ IFIPE JAVBF M~E OCL RIA RIE AAYXX CITATION
ID	FETCH-LOGICAL-c132t-d3df8dde432d145f32130f9081f1f7f2225178e8b95c84eac65cd541c2efb6ad3
IEDL.DBID	RIE
ISSN	2691-4581
IngestDate	Sat Nov 29 07:38:39 EST 2025 Wed Aug 27 07:40:20 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	12
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c132t-d3df8dde432d145f32130f9081f1f7f2225178e8b95c84eac65cd541c2efb6ad3
ORCID	0000-0002-8051-9747 0000-0001-9069-770X 0000-0003-4793-003X 0000-0001-8075-6243
PageCount	16
ParticipantIDs	crossref_primary_10_1109_TAI_2024_3464511 ieee_primary_10684843
PublicationCentury	2000
PublicationDate	2024-Dec.
PublicationDateYYYYMMDD	2024-12-01
PublicationDate_xml	– month: 12 year: 2024 text: 2024-Dec.
PublicationDecade	2020
PublicationTitle	IEEE transactions on artificial intelligence
PublicationTitleAbbrev	TAI
PublicationYear	2024
Publisher	IEEE
Publisher_xml	– name: IEEE
References	ref13 Christie (ref44) 1962 ref57 ref12 ref56 ref15 ref59 ref14 ref58 ref52 ref11 ref55 ref10 ref54 ref17 ref16 ref19 ref18 ref51 ref50 ref46 ref45 ref48 ref47 ref41 Goodfellow (ref37) 2015 ref43 ref49 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 ref35 ref34 ref36 ref31 ref30 ref33 ref32 ref2 ref1 Christie (ref42) 1962 ref39 Raghunathan (ref38) 2020 ref24 ref23 ref26 ref25 ref20 ref22 ref21 Kurakin (ref53) 2017 ref28 ref27 ref29 ref60 ref62 ref61
References_xml	– ident: ref22 doi: 10.1109/TII.2022.3178418 – ident: ref52 doi: 10.1109/TPEL.2022.3206239 – ident: ref62 doi: 10.1109/TSP.2019.2955832 – ident: ref17 doi: 10.1109/GlobalSIP45357.2019.8969373 – ident: ref46 doi: 10.1109/CIT/IUCC/DASC/PICOM.2015.90 – ident: ref50 article-title: Backcasted (actual) load profiles-historical – ident: ref29 doi: 10.1109/ITNEC52019.2021.9587009 – ident: ref32 doi: 10.1109/TSG.2020.3010510 – ident: ref31 doi: 10.1109/AIPR50011.2020.9425190 – volume-title: Univ. of Washington year: 1962 ident: ref42 article-title: Power systems test case archive: 14 bus power flow test case – ident: ref18 doi: 10.1109/JSYST.2019.2927469 – volume-title: Univ. of Washington year: 1962 ident: ref44 article-title: Power systems test case archive: 118 bus power flow test case – ident: ref21 doi: 10.1109/TII.2023.3290942 – ident: ref54 doi: 10.1109/SP.2017.49 – ident: ref30 doi: 10.1109/TCYB.2021.3125345 – ident: ref8 doi: 10.1109/AIAM50918.2020.00033 – ident: ref1 doi: 10.1109/TPWRS.2021.3091616 – ident: ref60 doi: 10.1109/TPWRS.2016.2634318 – ident: ref19 doi: 10.1109/JSYST.2021.3136683 – ident: ref34 doi: 10.1109/JIOT.2022.3147040 – ident: ref45 doi: 10.1109/TSG.2016.2540439 – ident: ref28 doi: 10.1109/TSG.2020.3047864 – ident: ref14 doi: 10.1109/JIOT.2021.3113900 – ident: ref15 doi: 10.1109/JIOT.2020.2983911 – ident: ref9 doi: 10.1016/j.jisa.2019.02.008 – ident: ref4 doi: 10.1109/TETCI.2019.2902845 – ident: ref24 doi: 10.1109/TII.2021.3102332 – ident: ref6 doi: 10.1109/TSG.2022.3193989 – ident: ref23 doi: 10.1109/TSG.2021.3109628 – ident: ref41 doi: 10.1109/TSG.2019.2947148 – ident: ref7 doi: 10.1109/JSYST.2014.2341597 – ident: ref10 doi: 10.1109/TSG.2019.2949998 – ident: ref47 doi: 10.1103/PhysRevE.83.036106 – ident: ref43 doi: 10.1109/TPAS.1979.319407 – start-page: 1 volume-title: Proc. Int. Conf. Learn. Representations (ICLR) year: 2017 ident: ref53 article-title: Adversarial examples in the physical world – ident: ref55 doi: 10.1109/TNNLS.2023.3274538 – ident: ref27 doi: 10.1109/TAI.2023.3286831 – ident: ref58 doi: 10.1109/TAI.2021.3096489 – ident: ref61 doi: 10.1109/TSG.2010.2044814 – ident: ref49 doi: 10.1109/TPWRS.2010.2051168 – ident: ref36 doi: 10.23919/EUSIPCO55093.2022.9909779 – ident: ref59 doi: 10.2991/msam-17.2017.68 – ident: ref25 doi: 10.1109/TSG.2023.3261970 – ident: ref2 doi: 10.1109/TSG.2022.3204796 – ident: ref3 doi: 10.1109/JSYST.2021.3109082 – ident: ref20 doi: 10.1109/TII.2018.2825243 – ident: ref5 doi: 10.1109/TETCI.2022.3232821 – ident: ref26 doi: 10.1109/TII.2023.3281664 – year: 2020 ident: ref38 article-title: Certified defenses against adversarial examples – volume-title: Proc. Int. Conf. Learn. Representations (ICLR) year: 2015 ident: ref37 article-title: Explaining and harnessing adversarial examples – ident: ref48 doi: 10.1007/978-0-387-30164-8 – ident: ref57 doi: 10.1007/978-3-319-33331-1_16 – ident: ref12 doi: 10.1109/CSCI.2017.1 – ident: ref13 doi: 10.1109/TSG.2020.3010510 – ident: ref40 doi: 10.1109/MITS.2014.2324023 – ident: ref35 doi: 10.1109/ACCESS.2023.3323617 – ident: ref56 doi: 10.1109/JSYST.2020.3030238 – ident: ref51 doi: 10.1109/JSYST.2022.3231897 – ident: ref11 doi: 10.1109/ACCESS.2019.2902910 – ident: ref16 doi: 10.1109/TAI.2021.3076021 – ident: ref33 doi: 10.1109/TII.2023.3331544 – ident: ref39 doi: 10.1145/3133956.3134057
SSID	ssj0002512227
Score	2.2754688
Snippet	Smart power grids are vulnerable to security threats due to their cyber-physical nature. Existing data-driven detectors aim to address simple traditional false...
SourceID	crossref ieee
SourceType	Index Database Publisher
StartPage	6601
SubjectTerms	Accuracy Artificial intelligence Cyber-physical systems security cyberattacks Detectors evasion attacks false data injection attacks (FDIAs) graph autoencoder graph neural networks (GNNs) machine learning Robustness Smart grids Topology Training
Title	Spatio-temporal Graph-Based Generation and Detection of Adversarial False Data Injection Evasion Attacks in Smart Grids
URI	https://ieeexplore.ieee.org/document/10684843
Volume	5
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 2691-4581 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002512227 issn: 2691-4581 databaseCode: RIE dateStart: 20200101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2691-4581 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002512227 issn: 2691-4581 databaseCode: M~E dateStart: 20200101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV05T8MwFLZoxcBCOYooR-WBhcGlPhI7Y4EWKkGF1CJ1i-JLKoIUtSls_HZsJ0VlYGCLIluJ_N7zO753AHAhreRRoiSyVkjEYqGdSGUUxZRIjTkmXR36zD7w0UhMp8lTVaweamGMMSH5zHT8Y8Dy9VytfKjMSXgsmGC0Bmqcx2Wx1k9AxStqQvgaiuwmV5Pe0DmAhHWoh-8w_qV6NmapBFUyaPzzJ_bAbmUzwl5J5H2wZfID0FjPY4CVeB6Cz3FIj0ZVu6lXeOe7UaNrp6g0LPtLezLALNfw1hQhCSuHcwvDVOZl5nkRDhw_GnibFRkc5i_VGmdv-6ga7BWFr8mHsxyO3xzTuS_M9LIJngf9yc09qgYrIOWczwJpqq1w9xqjRGMWWUqcJrOJsw4sttx6FxBzYYRMIiWYu5rjSOmIYUWMlXGm6RGo5_PcHANorIfTVdejqYxSljEaaw_Faiqp0wMtcLk-8_S97J-RBr-jm6SOPqmnT1rRpwWa_rg31pUnffLH-1Ow47eXySVnoF4sVuYcbKuPYrZctEHt8avfDjzyDaksu5M
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELagIMFCeYry9MDCkBI_kjhjoZRWlAqpReoWxbEtFUGK2hT-Pj4nRWVgYIsiy4l8d77Hdw-ErqSRURBn0jNGSI-HQlmRSpkXMioViQj1lesz248GAzEex89VsbqrhdFau-Qz3YRHh-WrabaAUJmV8FBwwdk62oDRWVW51k9IBVQ1pdESjPTjm1GrZ11AypsMADxCfimflWkqTpl06v_8jV20U1mNuFWSeQ-t6Xwf1ZcTGXAloAfoa-gSpL2q4dQbfoB-1N6tVVUKlx2mgRA4zRVu68KlYeV4arCbyzxPgRtxx3Kkxu20SHEvf63WWIsb4mq4VRRQlY8nOR6-W7azX5io-SF66dyP7rpeNVrBy6z7WXiKKSPszcYZVYQHhlGry0xs7QNDTGTACSSR0ELGQSa4vZzDIFMBJxnVRoapYkeolk9zfYywNgCoZz7gqZwxnnIWKgBjFZPMaoIGul6eefJRdtBInOfhx4mlTwL0SSr6NNAhHPfKuvKkT_54f4m2uqOnftLvDR5P0TZsVaaanKFaMVvoc7SZfRaT-ezCcco3KCu9qw
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Spatio-temporal+Graph-Based+Generation+and+Detection+of+Adversarial+False+Data+Injection+Evasion+Attacks+in+Smart+Grids&rft.jtitle=IEEE+transactions+on+artificial+intelligence&rft.au=Takiddin%2C+Abdulrahman&rft.au=Ismail%2C+Muhammad&rft.au=Atat%2C+Rachad&rft.au=Serpedin%2C+Erchin&rft.date=2024-12-01&rft.pub=IEEE&rft.eissn=2691-4581&rft.volume=5&rft.issue=12&rft.spage=6601&rft.epage=6616&rft_id=info:doi/10.1109%2FTAI.2024.3464511&rft.externalDocID=10684843
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2691-4581&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2691-4581&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2691-4581&client=summon