On the Feasibility of Profiling Electric Vehicles through Charging Data

TL;DR

This study investigates the potential privacy risks of profiling electric vehicles through charging data, proposing an improved method and evaluating its effectiveness, ultimately finding that individual EV profiling remains impractical with current data types.

Contribution

The paper introduces an enhanced EV profiling technique and provides a comprehensive real-world evaluation demonstrating its limited practical effectiveness.

Findings

Profiling EVs is not feasible at scale with current analog charging data.

The improved profiling approach outperforms previous methods in controlled experiments.

Results support increased trust in EV privacy and promote adoption.

Abstract

Electric vehicles (EVs) represent the long-term green substitute for traditional fuel-based vehicles. To encourage EV adoption, the trust of the end-users must be assured. In this work, we focus on a recently emerging privacy threat of profiling and identifying EVs via the analog electrical data exchanged during the EV charging process. The core focus of our work is to investigate the feasibility of such a threat at scale. To this end, we first propose an improved EV profiling approach that outperforms the state-of-the-art EV profiling techniques. Next, we exhaustively evaluate the performance of our improved approach to profile EVs in real-world settings. In our evaluations, we conduct a series of experiments including 25032 charging sessions from 530 real EVs, sub-sampled datasets with different data distributions, etc. Our results show that even with our improved approach, profiling and individually identifying the growing number of EVs is not viable in practice; at least with the analog charging data utilized throughout the literature. We believe that our findings from this work will further foster the trust of potential users in the EV ecosystem, and consequently, encourage EV adoption.