Blending Data and Physics Against False Data Injection Attack: An Event-Triggered Moving Target Defence Approach

IEEE Transactions on Smart Grid - Tập 14 Số 4 - Trang 3176-3188 - 2023
Wangkun Xu1, Martin Higgins2, Jianhong Wang1, Imad M. Jaimoukha1, Fei Teng1
1Department of Electrical and Electronic Engineering, Imperial College London, London, U.K.
2Department of Engineering Science, University of Oxford, Oxford, U.K.

Tóm tắt

Fast and accurate detection of cyberattacks is a key element for a cyber-resilient power system. Recently, data-driven detectors and physics-based Moving Target Defences (MTD) have been proposed to detect false data injection (FDI) attacks on state estimation. However, the uncontrollable false positive rate of the data-driven detector and the extra cost of frequent MTD usage limit their wide applications. Few works have explored the overlap between these two areas. To fill this gap, this paper proposes blending data-driven and physics-based approaches to enhance the detection performance. To start, a physics-informed data-driven attack detection and identification algorithm is proposed. Then, an MTD protocol is triggered by the positive alarm from the data-driven detector. The MTD is formulated as a bilevel optimisation to robustly guarantee its effectiveness against the worst-case attack around the identified attack vector. Meanwhile, MTD hiddenness is also improved so that the defence cannot be detected by the attacker. To guarantee feasibility and convergence, the convex two-stage reformulation is derived through duality and linear matrix inequality. The simulation results verify that blending data and physics can achieve extremely high detection rate while simultaneously reducing the false positive rate of the data-driven detector and the extra cost of MTD. All codes are available at https://github.com/xuwkk/DDET-MTD.

Từ khóa

#Smart grid #FDI attacks #attack detection and identification #moving target defence #state estimation

Tài liệu tham khảo

10.1109/TPWRS.2020.3010365

10.1109/TEVC.2017.2712906

10.1007/s10207-022-00621-7

10.1109/TPWRS.2019.2938223

10.1109/TSG.2022.3170839

wang, 2021, Multi-agent reinforcement learning for active voltage control on power distribution networks, Proc Adv Neural Inf Process Syst, 34, 3271

10.1109/TPWRS.2022.3152801

10.1109/TSG.2021.3107972

10.1109/TSG.2022.3156445

10.1109/ACCESS.2021.3058628

10.1109/TSG.2020.2977207

10.1109/ACCESS.2021.3128035

10.1109/TIFS.2019.2928624

kingma, 2014, Adam: A method for stochastic optimization, arXiv 1412 6980

10.1109/TSG.2016.2544854

mahmoud, 2021, Cyberphysical Infrastructures in Power Systems Architectures and Vulnerabilities

10.1109/TSG.2018.2791512

diamond, 2016, CVXPY: A python-embedded modeling language for convex optimization, J Mach Learn Res, 17, 1

10.1109/TIFS.2022.3210864

paszke, 2019, Pytorch: An imperative style, high-performance deep learning library, Proc Adv Neural Inf Process Syst, 32, 8024

10.1109/TSG.2021.3076824

10.1145/3372751

xu, 2020, A deep learning based detection method for combined integrity-availability cyber attacks in power system, arXiv 2011 01816

10.1109/TSG.2020.3010510

10.1145/3384941.3409588

10.1145/3439950

10.1049/cps2.12002

10.1109/CDC.2015.7403200

10.1017/CBO9780511804441

10.1109/TII.2020.2984315

10.1109/ISGT-Europe54678.2022.9960436

zimmerman, 2018, Matpower User’s Manual Version 7 0

10.1109/TSG.2016.2596298

10.1201/9780203913673

10.1145/2663474.2663482

10.1109/PESGM46819.2021.9638211

10.1109/JSTSP.2018.2846542

10.1109/TII.2016.2614396

10.1109/TSG.2012.2195338

10.1109/TSG.2022.3141803

bellizio, 2022, Transition to digitalized paradigms for security control and decentralized electricity market, Proc IEEE, 10.1109/JPROC.2022.3161053

gallier, 2010, Notes on the Schur Complement

Thông tin
Thông tin xuất bản

IEEE Transactions on Smart Grid

Tập 14 Số 4

3176-3188

Thông tin tác giả