A New AC False Data Injection Attack Method Without Network Information

Abstract

Cyberattack emerges as a critical concern in Internet-of-Things integrated power systems. Cybersecurity capabilities of power systems rely on a deep understanding of potential cyberattacks for identifying and protecting against cyber vulnerabilities. The common assumption of system network information in most existing works is suspicious, which fails to hold in practical fields. This paper proposes a novel data-driven false data injection attack method, where only easily accessible measurement data are required, i.e., power injections at buses, flows of lines and the tie line information (connection relationship and power measurement data). In the proposed method, generative adversarial network (GAN) is adopted to extract the physical model using historical measurement data, and a self-attention mechanism is integrated to further capture the power flow laws in the data. After offline training, the effective false data can be constructed in a timely fashion without system network information. The effectiveness of the proposed attack method is validated using the IEEE14 and IEEE118 systems, in which the constructed false data injection attack can evade the system residual detection with an average success rate over 90% under different levels of measuring errors.