Moving Target Defense Against Adversarial False Data Injection Attacks In Power Grids
Yexiang Chen, Subhash Lakshminarayana, H. Vincent Poor
TL;DR
This paper tackles adversarial false data injection attacks on power-grid state estimation by proposing a moving target defense that blends an MTD-strengthened DNN with a physics-based MTD. A model pool of diverse DNN detectors is trained and periodically refreshed to randomize decision boundaries and reduce attack transferability, achieving high detection recall while maintaining efficiency. To further limit operational costs, the authors couple the DNN ensemble with D-FACTS-based topology perturbations, aided by meta-learning for rapid adaptation to new topologies. Simulation results on IEEE 14/30/118-bus systems show detection recall above 99% when physics-based MTD is employed, with only moderate increases in OPF cost, demonstrating practical viability for defending against both BDD-bypassing FDIAs and adversarial perturbations aimed at the DNNs.
Abstract
Machine learning (ML)-based detectors have been shown to be effective in detecting stealthy false data injection attacks (FDIAs) that can bypass conventional bad data detectors (BDDs) in power systems. However, ML models are also vulnerable to adversarial attacks. A sophisticated perturbation signal added to the original BDD-bypassing FDIA can conceal the attack from ML-based detectors. In this paper, we develop a moving target defense (MTD) strategy to defend against adversarial FDIAs in power grids. We first develop an MTD-strengthened deep neural network (DNN) model, which deploys a pool of DNN models rather than a single static model that cooperate to detect the adversarial attack jointly. The MTD model pool introduces randomness to the ML model's decision boundary, thereby making the adversarial attacks detectable. Furthermore, to increase the effectiveness of the MTD strategy and reduce the computational costs associated with developing the MTD model pool, we combine this approach with the physics-based MTD, which involves dynamically perturbing the transmission line reactance and retraining the DNN-based detector to adapt to the new system topology. Simulations conducted on IEEE test bus systems demonstrate that the MTD-strengthened DNN achieves up to 94.2% accuracy in detecting adversarial FDIAs. When combined with a physics-based MTD, the detection accuracy surpasses 99%, while significantly reducing the computational costs of updating the DNN models. This approach requires only moderate perturbations to transmission line reactances, resulting in minimal increases in OPF cost.