Summary
The rapid growth of electric vehicle (EV) adoption has made charging infrastructures a critical component of modern mobility and energy systems. This evolution, however, introduces significant cybersecurity challenges, as EV charging networks increasingly interconnect physical assets with digital platforms, thereby expanding the attack surface. This paper proposes a modular and non-intrusive monitoring and anomaly-detection platform designed to enhance the cyber resilience of Electric Vehicle Supply Equipment (EVSE).The proposed platform integrates real-time traffic monitoring with AI-based anomaly-detection techniques and supports heterogeneous data sources and industrial communication protocols, including
Read more Read lessOCPP and IEC 61850. To address the limited availability of real operational datasets, a synthetic data-generation approach based on a Wasserstein Generative Adversarial Network
(W-GAN) with residual LSTM layers is adopted to produce realistic OCPP traffic patterns and improve the training of detection models. The effectiveness of the proposed solution is demonstrated through experimental validation on a real, multi-vendor EV charging testbed, where the platform successfully identifies anomalous behaviours and Distributed Denial-ofService (DDoS) attacks. The results show that the combination of AI-driven monitoring and synthetic data augmentation significantly improves anomaly-detection capabilities, contributing to stronger cybersecurity and regulatory compliance for e-mobility infrastructures.
Additional informations
| Publication type | Session Materials |
|---|---|
| Reference | D2_11145_2026 |
| Publication year | |
| Publisher | CIGRE |
| Country | Italy |
| Study committees | |
| File size | 1 MB |
| Price for non member | 30 € |
| Price for member | 30 € |
Authors
TERRUGGIA Roberta - RSE
Keywords
Cybersecurity, Artificial Intelligence, EV Charging Infrastructure, ICT Monitoring, CyberAttack Detection, e-Mobility
