This paper proposes a novel deep learning-based radio frequency fingerprint (RFF) identification method for internet of things (IoT) terminal authentications. Differential constellation trace figure (DCTF), a two-dimensional (2D) representation of differential relationship of signal time series, is utilized to extract RFF features without requiring any synchronization. A convolutional neural network (CNN) is then designed to identify different devices using DCTF features. Compared to the existing CNN-based RFF identification methods, the proposed DCTF-CNN possesses the merits of high identification accuracy, zero prior information and low complexity. Experimental results have demonstrated that the proposed DCTF-CNN can achieve an identification accuracy as high as 99.1% and 93.8% under SNR levels of 30 dB and 15 dB, respectively, when classifying 54 target ZigBee devices, which significantly outperforms the existing RFF identification methods.

Radio frequency fingerprint identification (RFFI) is an emerging device authentication technique that relies on the intrinsic hardware characteristics of wireless devices. This paper designs a deep learning-based RFFI scheme for Long Range (LoRa) systems. Firstly, the instantaneous carrier frequency offset (CFO) is found to drift, which could result in misclassification and significantly compromise the stability of the deep learning-based RFFI system. CFO compensation is demonstrated to be effective mitigation. Secondly, three signal representations for deep learning-based RFFI are investigated in time, frequency, and time-frequency domains, namely in-phase and quadrature (IQ) samples, fast Fourier transform (FFT) results and spectrograms, respectively. For these signal representations, three deep learning models are implemented, i.e., multilayer perceptron (MLP), long short-term memory (LSTM) network and convolutional neural network (CNN), in order to explore an optimal framework. Finally, a hybrid classifier that can adjust the prediction of deep learning models with the estimated CFO is designed to further increase the classification accuracy. The CFO will not change dramatically over several continuous days, hence it can be used to correct predictions when the estimated CFO is much different from the reference one. Experimental evaluation is performed in real wireless environments involving 25 LoRa devices and a Universal Software Radio Peripheral (USRP) N210 platform. The spectrogram-CNN model is found to be optimal for classifying LoRa devices which can reach an accuracy of 96.40% with the least complexity and training time.

Radio frequency (RF) fingerprint is the inherent hardware characteristics and has been employed to classify and identify wireless devices in many Internet of Things (IoT) applications. This paper extracts novel RF fingerprint features, designs a hybrid and adaptive classification scheme adjusting to the environment conditions, and carries out extensive experiments to evaluate the performance. In particular, four modulation features, namely differential constellation trace figure (DCTF), carrier frequency offset, modulation offset and I/Q offset extracted from constellation trace figure (CTF), are employed. The feature weights under different channel conditions are calculated at the training stage. These features are combined smartly with the weights selected according to the estimated signal to noise ratio (SNR) at the classification stage. We construct a testbed using universal software radio peripheral (USRP) platform as the receiver and 54 ZigBee nodes as the candidate devices to be classified, which are the most ZigBee devices ever tested. Extensive experiments are carried out to evaluate the classification performance under different channel conditions, namely line-of-sight (LOS) and non-line-of-sight (NLOS) scenarios. We then validate the robustness by carrying out the classification process 18 months after the training, which is the longest time gap. We also use a different receiver platform for classification for the first time. The classification error rate is as low as 0.048 in LOS scenario, and 0.1105 even when a different receiver is used for classification 18 months after the training. Our hybrid classification scheme has thus been demonstrated effective in classifying a large amount of ZigBee devices.

With the increasing popularity of the Internet of Things (IoT), device identification, and authentication has become a critical security issue. Recently, radio frequency (RF) fingerprint-based identification schemes have attracted wide attention as they extract the inherent characteristics of hardware circuits which is very hard to forge. However, existing RF fingerprint-based approaches face the problems of unstable region of interest (ROI), high-cost feature design, and incomplete automation. To address these problems, this paper proposes a multisampling convolutional neural network (MSCNN) to extract RF fingerprint from the selected ROI for classifying ZigBee devices. A signal-to-noise ratio (SNR) adaptive ROI selection algorithm is also developed to alleviate the effect of semi-steady behavior of ZigBee devices owing to sleep mode switching. The proposed MSCNN uses multiple downsampling transformations for multiscale feature extraction and classification automatically. To validate and evaluate the performance of our proposed method, we design a testbed consisting of one low-cost universal software radio peripheral (USRP) as the receiver and 54 CC2530 devices as targets for identification. Extensive experiments are conducted to demonstrate the feasibility and reliability of MSCNN both in the line-of-sight (LOS) scenarios and non-LOS (NLOS) scenarios. The classification accuracy is as high as 97% under the LOS scenarios around SNR = 30 dB. Our scheme is robust over a wide range of SNRs under the LOS scenarios as well as under the NLOS scenarios.

Random and high-agreement secret key generation from noisy wideband channels is challenging due to the autocorrelation inside the channel samples and compromised cross correlation between channel measurements of two keying parties. This paper studies the signal preprocessing algorithms to establish high-agreement uncorrelated secret key in the presence of channel independent eavesdroppers. We first propose a general mathematical model for various preprocessing schemes, including principal component analysis (PCA), discrete cosine transform (DCT) and wavelet transform (WT). Among preprocessing schemes, PCA is proved to achieve the optimal secret key rate. Next, PCA with common eigenvector has been found to outperform PCA with private eigenvector in terms of an overall consideration of key agreement, information leakage, and computational expense. Then, we propose a system level design of key generation, including quantization, information reconciliation, and privacy amplification. Numerical results verify that the key generation enhanced by PCA with common eigenvector can achieve secret key with high key generation rate, low key error rate, and good randomness.

Radio frequency fingerprint (RFF) is an intrinsic hardware characteristic and has been employed for device identification. Its application in low signal-to-noise-ratio (SNR) has never been explored because its identification performance is greatly affected by the received signal quality. This paper proposes a novel RFF identification scheme for spread spectrum systems in low SNR scenarios. In the scheme, a signal preprocessing method, information data estimation based stacking (IDES) algorithm, is proposed, which leverages the repeated spreading sequences and stacks them together to eliminate the noise and interference effect. Simulation results demonstrate that the proposed scheme can achieve 98% identification rate when the received signal SNR is - 15 dB and the length of spreading sequence is 1023.