.png){kind=icon}
.png){kind=icon}
Return
Fine-Grained Vehicle Classification Using Loop Detectors: A Wireless Fingerprinting Approach
.png){kind=icon}
PRE
AI
A
A
L
R
M
DOI：10.1109/tits.2026.3696994.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The lack of secure identification of vehicles poses multiple threats to a rapidly growing intelligent transportation system. One notable threat is the impersonation of an authorized vehicle to deceive the automated vehicle access control (VAC) system, designed to prevent unauthorized vehicles from entering restricted areas or accessing special privileges. Another potential attack involves battery electric vehicles (BEVs), wherein an adversary that has compromised the BEV’s software system deceives a charging station (plug-in or wireless) into overcharging the vehicle to produce catastrophic failure of the battery pack, including combustion or explosion. To address these threats we propose to identify vehicles, and hence their privileges and/or charging capabilities, using device fingerprinting. In particular, we leverage inductive loop detectors (ILD) to determine the make, model, and year of vehicles. A wide-band signal is used to capture unique frequency-dependent features of a vehicle resulting from its size, shape, metal structure, and content. An ILD-based approach is cost-effective to implement as it utilizes an already widely deployed infrastructure, in contrast to approaches that use surveillance cameras or other sensors. A circuit-level, low-cost, drop-in replacement to enable existing ILD deployments to fingerprint vehicles is proposed and realized as a custom, open-source PCB. A comprehensive evaluation against a dataset acquired from 32 vehicles of different make, model, and year, over nine months, shows that the proposed approach is effective even under temporal, environmental, and measurement variation without retraining. Overall multi-class classification accuracy of up to 93% is achieved.
Keywords:
Vehicle security
vehicle classification
VMMR
security of electric vehicles
Journal
IF:
8.4
Papers:
9.5K
Citations:
6.3W
Organization
Cited Papers