Matrix-Completion-Based False Data Injection Attacks Against Machine Learning Detectors
Matrix-Completion-Based False Data Injection Attacks Against Machine Learning Detectors
复制标题
DOI：
10.1109/tsg.2023.3308339
复制
发表时间：
2024-03
影响因子：
9.6
通讯作者：
Bo Liu;Hongyu Wu;Qihui Yang;Hang Zhang;Yajing Liu;Y. Zhang
中科院分区：
文献类型：
--
作者：
Bo Liu;Hongyu Wu;Qihui Yang;Hang Zhang;Yajing Liu;Y. Zhang
虚假数据注入（FDI）攻击可以操纵电力系统测量，导致系统的经济损失和安全问题。虽然机器学习（ML）检测器可以有效地检测FDI攻击，但目前用于构建FDI攻击的方法没有考虑ML检测器的存在。为了解决这个问题，我们提出了新的凸矩阵完成为基础的FDI（MC-FDI）攻击DC和AC潮流模型从攻击者的角度来看，占妥协和历史测量之间的时间相关性。所提出的攻击最小化妥协测量矩阵的核范数，使妥协测量与历史测量一致，并最大化增量电压角的L1范数，以确保对电力系统运行的足够的负面影响。移动目标防御（MTD）提出了检测拟议的MC-FDI攻击从防御者的立场。其思想是主动改变线路阻抗，以破坏MC-FDI攻击中受损测量的空间和时间相关性。在IEEE 14节点和IEEE 118节点系统上的仿真结果表明，该攻击对卡方检测器和ML检测器都具有隐蔽性，MTD在检测MC-FDI攻击中也具有较好的效果.
False data injection (FDI) attacks can manipulate power system measurements, leading to system economic losses and security issues. Although machine-learning (ML) detectors can effectively detect FDI attacks, the current methods used to construct FDI attacks do not take into account the presence of ML detectors. To tackle this problem, we propose novel convex matrix-completion-based FDI (MC-FDI) attacks on DC and AC power flow models from an attacker’s perspective, accounting for the temporal correlation between compromised and historical measurements. The proposed attacks minimize the nuclear norm of the compromised measurement matrix to make the compromised measurement consistent with the historical measurements, and also maximize the L1-norm of the incremental voltage angle to ensure a sufficient negative impact on the power system operation. Moving target defense (MTD) is proposed to detect the proposed MC-FDI attacks from the defender’s standpoint. The idea is to actively change the line impedance to corrupt the spatial and temporal correlation of the compromised measurements in the MC-FDI attacks. Numerical results on the IEEE 14-bus and IEEE 118-bus systems show the stealthiness of the proposed attacks to both the Chi-square detector and ML detectors as well as the efficacy of MTD in detecting the MC-FDI attacks.