The machine learning (ML) sees an increasing prevalence of being used in the internet-of-things enabled smart grid. However, the trustworthiness of ML is a severe issue that must be addressed to accommodate the trend of ML-based smart grid applications (MLsgAPPs). The adversarial distortion injected into the power signal will greatly affect the system's normal control and operation. Therefore, it is imperative to conduct vulnerability assessment for MLsgAPPs applied in the context of safety-critical power systems. In this paper, we provide a comprehensive review of the recent progress in designing attack and defense methods for MLsgAPPs. Unlike the traditional survey about ML security, this is the first review work about the security of MLsgAPPs that focuses on the characteristics of power systems. The survey is organized from the aspects of adversarial assumptions, targeted applications, evaluation metrics, defending approaches, physics-related constraints, and applied datasets. We also highlight future directions on this topic to encourage more researchers to conduct further research on adversarial attacks and defending approaches for MLsgAPPs.

翻译：机器学习在物联网智能电网中的应用日益普及。然而，为适应基于机器学习的智能电网应用（MLsgAPPs）的发展趋势，机器学习的可信度是一个必须解决的关键问题。注入电力信号中的对抗性扰动将严重影响系统的正常控制和运行。因此，对应用于安全关键电力系统背景下的MLsgAPPs进行脆弱性评估至关重要。本文全面综述了针对MLsgAPPs的攻击与防御方法设计的最新进展。与传统的机器学习安全综述不同，这是首篇聚焦电力系统特性的MLsgAPPs安全综述工作。本综述从对抗性假设、目标应用、评估指标、防御方法、物理相关约束及所采用数据集等方面进行组织。此外，我们强调了该课题的未来研究方向，以鼓励更多研究者对MLsgAPPs的对抗攻击与防御方法开展进一步研究。