# Stealthy, High-Impact False Data Injection Attacks in Smart Grid Using Physics-Constrained GAN

DevFeed: [Stealthy, High-Impact False Data Injection Attacks in Smart Grid Using Physics-Constrained GAN](<https://devfeed.tech/articles/stealthy-high-impact-false-data-injection-attacks-in-smart-grid-using-physics-constrained-gan-132965.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.15162>)

Author: Md. Mainul Islam, Hasan Kurban, Abdulrahman Takiddin, Muhammad Ismail, Rachad Atat, Erchin Serpedin

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Adversarial attacks](<https://devfeed.tech/topics/adversarial-attacks.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>)

Tags: [adversarial](<https://devfeed.tech/tags/adversarial.md>), [attacks](<https://devfeed.tech/tags/attacks.md>), [bdd](<https://devfeed.tech/tags/bdd.md>), [bus](<https://devfeed.tech/tags/bus.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-sy](<https://devfeed.tech/tags/cs-sy.md>), [demand](<https://devfeed.tech/tags/demand.md>), [eess-sy](<https://devfeed.tech/tags/eess-sy.md>), [evasion](<https://devfeed.tech/tags/evasion.md>), [impact](<https://devfeed.tech/tags/impact.md>), [learning](<https://devfeed.tech/tags/learning.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [measurement](<https://devfeed.tech/tags/measurement.md>), [measurements](<https://devfeed.tech/tags/measurements.md>), [network](<https://devfeed.tech/tags/network.md>), [performance](<https://devfeed.tech/tags/performance.md>), [physics](<https://devfeed.tech/tags/physics.md>), [pjm-interconnection](<https://devfeed.tech/tags/pjm-interconnection.md>), [power](<https://devfeed.tech/tags/power.md>), [smart-grid](<https://devfeed.tech/tags/smart-grid.md>), [synthetic](<https://devfeed.tech/tags/synthetic.md>), [transmission](<https://devfeed.tech/tags/transmission.md>)

## AI overview

PCGAN learns decoupled power-flow sensitivities from historical measurements of deployed sensors and uses them to guide realistic perturbations limited to compromised channels. In tests on the IEEE 300-bus system using observed PJM demand and synthetic bus-level profiles, it was compared with seven existing attacks at four sensor compromise levels, against ten ML detectors and conventional bad-data detection, with physical impact measured by nonlinear AC weighted least-squares state estimation. Across scenarios, PCGAN reported 84.28% mean ML evasion, 22.31% mean spatial load misperception, and an 18.69% mean stealth-impact score versus 5.61% for the strongest competing attack. It also evaded chi-square and largest-normalized-residual BDD at 83.45% and 86.02%, respectively.

## Source excerpt

arXiv:2611.15162v1 Announce Type: new Abstract: False data injection (FDI) attacks can distort power system state estimation while retaining plausible measurement patterns. Existing FDI methods trade stealth for impact or vice versa. They often assume access to internal grids, all-bus sensing, or defender models. In this paper, we propose a detector-agnostic physics-constrained generative adversarial network (PCGAN) that learns decoupled power-flow sensitivities from historical measurements of deployed sensors. The learned active-power-angle and reactive-power-voltage-magnitude relationships guide perturbations restricted to compromised channels, while adversarial training promotes realistic spatiotemporal patterns. We implement PCGAN and seven existing FDI attacks on the IEEE 300-bus system using one year of observed hourly demand from PJM Interconnection, a regional transmission organization in the United States, and synthetic bus-level load profiles. We compare their performance across 10%, 30%, 60%, and 100% compromised sensors. Attack stealth is assessed against ten machine-learning (ML) detectors and conventional bad-data detection (BDD) methods, while physical impact is quantified through nonlinear alternating-current weighted least-squares state estimation. PCGAN achieves 84.28% mean ML evasion and 22.31% mean spatial load misperception across the four scenarios. Its mean stealth-impact trade-off score reaches 18.69%, compared with 5.61% for the strongest competing attack. PCGAN also achieves 83.45% chi-square BDD evasion and 86.02% largest-normalized-residual BDD evasion. These results demonstrate a favorable stealth-impact balance under varying sensor-access levels and provide challenging attack cases for evaluating FDI detectors.