PHANTOM: Physics-Aware Adversarial Attacks against Federated Learning-Coordinated EV Charging Management System

2025-12-26

AI Summary

The large-scale integration of electric vehicle charging stations (EVCSs) into the vehicle-to-grid (V2G) ecosystem introduces significant adversarial attack risks, particularly cross-transmission-and-distribution-grid cascading false data injection attacks (FDIAs). Method: This paper proposes a physics-informed adversarial digital twin framework that integrates physics-informed neural networks (PINNs) with multi-agent reinforcement learning (DQN/SAC), deployed within a federated learning (FL)-based coordinated EV charging management architecture to generate highly stealthy, detection-evading attack strategies. Contribution/Results: Experimental validation on a co-simulation platform demonstrates that the proposed attack effectively induces voltage instability and load imbalance, while exposing deep security vulnerabilities—specifically, physical inconsistency—in FL-enabled power system control. This work establishes a novel paradigm for assessing and enhancing V2G resilience, providing both theoretical insight and empirical evidence for securing cyber-physical energy systems.

Technology Category

• Multiagent Systems: Adversarial Agents
• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Large-scale security measurements

Abstract

The rapid deployment of electric vehicle charging stations (EVCS) within distribution networks necessitates intelligent and adaptive control to maintain the grid's resilience and reliability. In this work, we propose PHANTOM, a physics-aware adversarial network that is trained and optimized through a multi-agent reinforcement learning model. PHANTOM integrates a physics-informed neural network (PINN) enabled by federated learning (FL) that functions as a digital twin of EVCS-integrated systems, ensuring physically consistent modeling of operational dynamics and constraints. Building on this digital twin, we construct a multi-agent RL environment that utilizes deep Q-networks (DQN) and soft actor-critic (SAC) methods to derive adversarial false data injection (FDI) strategies capable of bypassing conventional detection mechanisms. To examine the broader grid-level consequences, a transmission and distribution (T and D) dual simulation platform is developed, allowing us to capture cascading interactions between EVCS disturbances at the distribution level and the operations of the bulk transmission system. Results demonstrate how learned attack policies disrupt load balancing and induce voltage instabilities that propagate across T and D boundaries. These findings highlight the critical need for physics-aware cybersecurity to ensure the resilience of large-scale vehicle-grid integration.

Problem

• Develops adversarial attacks on EV charging systems using physics-aware AI
• Simulates cross-grid impacts of false data injection on power stability
• Highlights need for physics-informed cybersecurity in vehicle-grid integration

Innovation

• Physics-aware adversarial network using multi-agent reinforcement learning
• Digital twin with physics-informed neural network and federated learning
• Transmission-distribution dual simulation platform for cascading impact analysis