Research of Smart Car Key Security Identification Method Based on RF Fingerprint

• 1、School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing 100876

Abstract：In recent years, car keyless entry systems have become popular in smart cars, and they assume the important security function of resisting car theft and protecting the property inside the car, which leads to car keyless entry systems being the second most attacked system in smart cars. A class of physical layer-based attacks against car keyless entry systems is now increasingly reported and reproduced. This method is usually implemented through RF circuits, which perform recording-playback, relaying and other replication means on car key signals from the physical layer, and thus can bypass the encryption mechanism in the protocol layer of the car key system. Aiming at the characteristics of the security threats faced by the current car key system, this paper proposes an RF fingerprint-based security identification method for smart car keys. Seven types of RF fingerprint features are selected as the basis for identifying the signals by analyzing the modulation mode and protocol structure of car key signals. K-NN and SVM single classifiers are trained based on semi-supervised learning methods to conduct experiments on different attack scenarios. In this paper, the false negative rate (FNR) is defined as the proportion of illegal attack signals identified as legitimate signals.The average FNR in the experiments is 1.27% and FPR is 1.5%. The experimental results show that the method can effectively identify the illegal signals of car key physical layer attacks.

Keywords： Car Key Security RF Fingerprint One Class KNN One Class SVM