CNN-Based RF Fingerprinting Method for Securing Passive Keyless Entry and Start System

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.

Payload Symbol-Based Nonlinear RF Fingerprint for Wireless QPSK-OFDM Devices

Radio Frequency(RF) fingerprinting is one physical-layer authentication method for wireless communication, which uses the unique hardware characteristic of the transmitter to identify its true identity.To improve the performance of RF Fingerprint(RFF)based on preamble with fixed duration, a nonlinear RF fingerprinting method based on payload symbols is proposed for the wireless OFDM communication with the bit mapping scheme of QPSK. The wireless communication system is modeled as a Hammerstein system containing the nonlinear transmitter and multipath fading channel. A parameter separation technique based on orthogonal polynomial is presented for the estimation of the parameters of the Hammerstein system. The Hammerstein system parameter separation technique is firstly used to estimate the linear parameter with the training signal, which is used to compensate the adverse effect of the linear channel for the demodulation of the successive payload symbols. The demodulated payload symbols are further used to estimate the nonlinear coefficients of the transmitter with the Hammerstein system parameter separation technique again, which is used as the novel RFF for the authentication of the QPSK-OFDM device. Numerical simulations have verified the proposed method, which can also be extended to the OFDM signals with other bit mapping schemes.

A WKNN-based approach for NB-IoT sensors localization

With the recent introduction of NarrowBand Internet of Things(NB-IoT)technology in the 4th and 5th generations of mobile radio networks,the mobile communications context opens up significantly to the world of sensors.By means of NB-IoT,the mobile systems within 3GPP standardization introduce the peculiar functions of sensor networks,thus making it possible to satisfy very specific requirements with respect to those which characterize traditional mobile telecommunications.Among the functions of interest for sensor networks,the possibility of locating the positions of the sensors without an increase in costs and energy consumption of the sensor nodes is of utmost interest.The present work describes a procedure for locating the NB-IoT nodes based on the quality of radio signals received by the mobile terminals,which therefore does not require further hardware implementations on board the nodes.This procedure,based on the RF fingerprinting technique and on machine learning processing,has been tested experimentally and has achieved interesting performances.

Radio Frequency Fingerprint-Based Satellite TT&C Ground Station Identification Method

This study presents a radio frequency(RF)fingerprint identification method combining a convolutional neural network(CNN)and gated recurrent unit(GRU)network to identify measurement and control signals.The proposed algorithm(CNN-GRU)uses a convolutional layer to extract the IQ-related learning timing features.A GRU network extracts timing features at a deeper level before outputting the final identification results.The number of parameters and the algorithm’s complexity are reduced by optimizing the convolutional layer structure and replacing multiple fully-connected layers with gated cyclic units.Simulation experiments show that the algorithm achieves an average identification accuracy of 84.74% at a -10 dB to 20 dB signal-to-noise ratio(SNR)with fewer parameters and less computation than a network model with the same identification rate in a software radio dataset containing multiple USRP X310s from the same manufacturer,with fewer parameters and less computation than a network model with the same identification rate.The algorithm is used to identify measurement and control signals and ensure the security of the measurement and control link with theoretical and engineering applications.