The rapid growth of modern vehicles with advanced technologies requires strong security to ensure customer safety.One key system that needs protection is the passive key entry system(PKES).To prevent attacks aimed at ...The rapid growth of modern vehicles with advanced technologies requires strong security to ensure customer safety.One key system that needs protection is the passive key entry system(PKES).To prevent attacks aimed at defeating the PKES,we propose a novel radio frequency(RF)fingerprinting method.Our method extracts the cepstral coefficient feature as a fingerprint of a radio frequency signal.This feature is then analyzed using a convolutional neural network(CNN)for device identification.In evaluation,we conducted experiments to determine the effectiveness of different cepstral coefficient features and the convolutional neural network-based model.Our experimental results revealed that the Gammatone Frequency Cepstral Coefficient(GFCC)was the most compelling feature compared to Mel-Frequency Cepstral Coefficient(MFCC),Inverse Mel-Frequency Cepstral Coefficient(IMFCC),Linear-Frequency Cepstral Coefficient(LFCC),and Bark-Frequency Cepstral Coefficient(BFCC).Additionally,we experimented with evaluating the effectiveness of our method in comparison to existing approaches that are similar to ours.展开更多
基金supported by Institute of Information&communications Technology Planning&Evaluation(IITP)grant funded by the Korea Government(MIST)(No.2022-0-01022,Development of Collection and Integrated Analysis Methods of Automotive Inter/Intra System Artifacts through Construction of Event-Based Experimental System).
文摘The rapid growth of modern vehicles with advanced technologies requires strong security to ensure customer safety.One key system that needs protection is the passive key entry system(PKES).To prevent attacks aimed at defeating the PKES,we propose a novel radio frequency(RF)fingerprinting method.Our method extracts the cepstral coefficient feature as a fingerprint of a radio frequency signal.This feature is then analyzed using a convolutional neural network(CNN)for device identification.In evaluation,we conducted experiments to determine the effectiveness of different cepstral coefficient features and the convolutional neural network-based model.Our experimental results revealed that the Gammatone Frequency Cepstral Coefficient(GFCC)was the most compelling feature compared to Mel-Frequency Cepstral Coefficient(MFCC),Inverse Mel-Frequency Cepstral Coefficient(IMFCC),Linear-Frequency Cepstral Coefficient(LFCC),and Bark-Frequency Cepstral Coefficient(BFCC).Additionally,we experimented with evaluating the effectiveness of our method in comparison to existing approaches that are similar to ours.
