# Can Predictive Filters Detect Gradually Ramping False Data Injection Attacks Against PMUs?

arXiv: https://arxiv.org/abs/1905.02271 · HTML: https://mlsanity.com/paper/1905.02271/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2019.

## Built on by (most cited first, 2 of 2)

- [A Temporal Graph Neural Network for Cyber Attack Detection and Localization in Smart Grids](https://mlsanity.com/paper/2212.03390/) (2022)
- [Resilient Temporal GCN for Smart Grid State Estimation Under Topology Inaccuracies](https://mlsanity.com/paper/2410.16008/) (2024)

## Abstract (arXiv)

Intelligently designed false data injection (FDI) attacks have been shown to be able to bypass the chi2-test based bad data detector (BDD), resulting in physical consequences (such as line overloads) in the power system. In this paper, it is shown that if an attack is suddenly injected into the system, a predictive filter with sufficient accuracy is able to detect it. However, an attacker can gradually increase the magnitude of the attack to avoid detection, and still cause damage to the system.