Generalized Graph Neural Network-Based Detection of False Data Injection Attacks in Smart Grids
Generalized Graph Neural Network-Based Detection of False Data Injection Attacks in Smart Grids
复制标题
DOI：
10.1109/tetci.2022.3232821
复制
发表时间：
2023-06
影响因子：
5.3
通讯作者：
Abdulrahman Takiddin;R. Atat;Muhammad Ismail;Osman Boyaci;K. Davis;E. Serpedin
中科院分区：
文献类型：
--
作者：
Abdulrahman Takiddin;R. Atat;Muhammad Ismail;Osman Boyaci;K. Davis;E. Serpedin
虚假数据注入攻击（FDIA）对智能电网构成重大威胁。最近的工作重点是开发针对此类攻击的基于机器学习 (ML) 的防御策略。然而，现有策略提供的检测性能有限，因为它们（a）缺乏在检测机制中嵌入电力系统拓扑的空间方面的能力，（b）提供的特定于拓扑的检测不能很好地推广到拓扑中具有季节性重新配置的实际系统，或者（c）基于训练集中存在的仅可见的 FDIA 类型提供检测。因此，在本文中，我们的目标是开发一种防御策略，以提高针对未见过的攻击的泛化能力和检测性能。为了实现这一目标，我们提出了一种基于图自动编码器（GAE）的检测策略，该策略（a）捕获电力系统的时空特征，从而提供改进的检测性能，（b）在反映电力系统拓扑的各种实现的综合图上进行训练，因此提供更好的泛化能力，以及（c）有效地对抗看不见的FDIA。所提出的检测器在 14、39 和 118 总线系统的各种拓扑配置上进行了训练和测试，在针对未见的 FDIA 和未见的拓扑进行测试时，检测率 (DR) 分别为 93.6%、95.7% 和 99.1%。与现有的基于 ML 的策略相比，这意味着成本提高了 11.5 - 30\%$。
False data injection attacks (FDIAs) pose a significant threat to smart power grids. Recent efforts have focused on developing machine learning (ML)-based defense strategies against such attacks. However, existing strategies offer limited detection performance since they (a) lack the capability of embedding the spatial aspects of the power system topology in the detection mechanism, (b) offer topology-specific detection that does not generalize well to practical systems with seasonal reconfigurations in their topology, or (c) offer detection based on only seen types of FDIAs present in the training set. Therefore, in this paper, we aim to develop a defense strategy that offers an improved generalization ability and detection performance against unseen attacks. Towards this objective, we propose a graph autoencoder (GAE)-based detection strategy that (a) captures spatio-temporal features of power systems, hence, offering improved detection performance, (b) is trained on comprehensive graphs reflecting various realizations of power system topologies, hence, offering better generalization abilities, and (c) works effectively against unseen FDIAs. The proposed detector is trained and tested on various topological configurations from 14, 39, and 118-bus systems offering detection rates (DRs) of 93.6%, 95.7%, and 99.1%, respectively, when tested against unseen FDIAs and unseen topologies. This presents an improvement of $11.5 - 30\%$ compared to existing ML-based strategies.