A Graph Neural Network Multi-Task Learning-Based Approach for Detection and Localization of Cyberattacks in Smart Grids
A Graph Neural Network Multi-Task Learning-Based Approach for Detection and Localization of Cyberattacks in Smart Grids
复制标题
DOI：
10.1109/icassp49357.2023.10096822
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Abdulrahman Takiddin;R. Atat;Muhammad Ismail;K. Davis;E. Serpedin
中科院分区：
文献类型：
--
作者：
Abdulrahman Takiddin;R. Atat;Muhammad Ismail;K. Davis;E. Serpedin
针对智能电网测量数据的虚假数据注入攻击（FDIA）对系统的稳定性构成了威胁。当恶意实体发起网络攻击以操纵测量数据时，不同的网格组件将受到影响，从而导致故障。为了有效地缓解攻击，需要两个任务：确定系统的状态（正常运行/受攻击）和定位受攻击的总线/变电站。现有的缓解技术分别执行这些任务，并提供有限的检测性能。在本文中，我们提出了一种基于多任务学习的方法，该方法使用具有堆叠卷积Chebyshev图层的图神经网络（GNN）同时执行这两项任务。我们的研究结果表明，该模型具有上级系统状态识别和攻击定位能力，检测率分别为98.5 - 100%和99 - 100%，与基准相比提高了5 - 30%。
False data injection attacks (FDIAs) on smart power grids’ measurement data present a threat to system stability. When malicious entities launch cyberattacks to manipulate the measurement data, different grid components will be affected, which leads to failures. For effective attack mitigation, two tasks are required: determining the status of the system (normal operation/under attack) and localizing the attacked bus/power substation. Existing mitigation techniques carry out these tasks separately and offer limited detection performance. In this paper, we propose a multi-task learning-based approach that performs both tasks simultaneously using a graph neural network (GNN) with stacked convolutional Chebyshev graph layers. Our results show that the proposed model presents superior system status identification and attack localization abilities with detection rates of 98.5−100% and 99 − 100%, respectively, presenting improvements of 5 − 30% compared to benchmarks.