Radio Frequency Fingerprint Identification Research Articles

Slice combination convolutional neural network based radio frequency fingerprint identification for Internet of Things

Slice combination convolutional neural network based radio frequency fingerprint identification for Internet of Things

RF Fingerprinting Identification Based on Spiking Neural Network for LEO–MIMO Systems

Low earth orbit (LEO) satellites promise to be a source of innovation in wireless communication and their physical layer security deserves attention. However, many physical layer security techniques are hampered by excessive power consumption and high latency when used for LEO satellites. This letter proposes an energy-efficiency radio frequency fingerprinting identification (RFFI) method for LEO satellite communication systems based on spiking neural networks (SNN). In addition, we investigate a channel-independent RFF feature transformation and data augmentation to enhance system robustness. Numerical results show that our proposed model can yield identification accuracy up to 95.26% at a signal-to-noise ratio (SNR) of 25dB on orthogonal frequency division multiplexing (OFDM) signals, and reduces power consumption by 63.3% compared to existing models of comparable accuracy on FPGA.

Toward Length-Versatile and Noise-Robust Radio Frequency Fingerprint Identification

Radio frequency fingerprint identification (RFFI) can classify wireless devices by analyzing the signal distortions caused by intrinsic hardware impairments. Recently, state-of-the-art neural networks have been adopted for RFFI. However, many neural networks, e.g., multilayer perceptron (MLP) and convolutional neural network (CNN), require fixed-size input data. In addition, many IoT devices work in low signal-to-noise ratio (SNR) scenarios but the RFFI performance in such scenarios is often unsatisfactory. In this paper, we analyze the reason why MLP- and CNN-based RFFI systems are constrained by the input size. To overcome this, we propose four neural networks that can process signals of variable lengths, namely flatten-free CNN, long short-term memory (LSTM) network, gated recurrent unit (GRU) network, and transformer. We adopt data augmentation during training which can significantly improve the model’s robustness to noise. We compare two augmentation schemes, namely offline and online augmentation. The results show the online one performs better. During the inference, a multi-packet inference approach is further leveraged to improve the classification accuracy in low SNR scenarios. We take LoRa as a case study and evaluate the system by classifying 10 commercial-off-the-shelf LoRa devices in various SNR conditions. The online augmentation can boost the low-SNR classification accuracy by up to 50% and the multi-packet inference approach can further increase the accuracy by over 20%.

Cross-Receiver Radio Frequency Fingerprint Identification Based on Contrastive Learning and Subdomain Adaptation

Radio frequency fingerprint (RFF) identification is emerging as an attractive paradigm for physical layer security. Despite the exceptional accuracy achieved by deep learning (DL) based schemes, few works consider the cross-receiver scenario. The performance deteriorates significantly when the model is deployed on new receivers directly. To this end, a cross-receiver RFF learning scheme is proposed. First, an unsupervised pre-training method based on contrastive learning is utilized to extract receiver-agnostic features. Then, the model is optimized by subdomain adaptation to further improve identification performance. The proposed scheme does not require multiple labeled datasets from different receivers. And experimental results indicate that the proposed scheme effectively alleviates performance degradation in the cross-receiver scenario.

Adversarial attacks and active defense on deep learning based identification of GaN power amplifiers under physical perturbation

Deep learning (DL)-based radiofrequency (RF) fingerprinting identification has shown significantly growing importance in the wireless industry including 5G, IoT and Wireless Sensor Networks (WSN). However, there is little investigation on the robustness of the corresponding DL models against adversarial attacks and adversarial defense. This paper discusses the effects of four cutting-edge adversarial attacks on DL-based RF fingerprinting identification and provides a graphical analysis of RF feature perturbations following adversarial attacks. For the first time we also demonstrate the results of combined physical attack (i.e. tuning the drain currents of the power amplifiers) by tuning the physical features of the device hardware (i.e. drain current), and adversarial attacks on DL-based classifiers. Experimental results from 16 Gallium nitride (GaN) power amplifiers (PA) reveal that adversarial attacks can seriously deteriorate the accuracy of RF identification from about 100.00% to below 10.00% even with only 0.50% adversarial perturbation. In order to deal with the problem of decreased accuracy caused by attacks, we proposed an adversarial defense method based on feature-level interpretability (FIAT), which improved the accuracy of RF identification with interpretability analysis. The results compared with several common defense methods validate that the proposed FIAT can maintain an accuracy of 96.00% even when the adversarial attack perturbation is 5.00% and with physical attack. Moreover, the changes of data features in the process of adversarial attacks and defense are given, providing a new way for the interpretability of adversarial attacks and defense on RF identification tasks.

A practical radio frequency fingerprinting scheme for mobile phones identification

Radio frequency fingerprint (RFF) has attracted a remarkable surge of attention to wireless transmitter identification due to the inimitable hardware imperfection. However, most RFF-based schemes devised in controlled environments are unable to reach the claimed performance in real-world scenarios. This paper proposes a practical RFF identification method for mobile phones in Global System for Mobile (GSM) system. Specifically, the instantaneous amplitude of near-transient part in normal burst (NB) is regarded as RFF that extracted from up-link communications. In addition, an anomaly filtering and stacking (AFS) method is introduced to obtain stable RFF in Time Division Multiple Access (TDMA) system. Lastly, the impacts of frequency point and sending power variations on RFF are fully dissected in comparison experiments. Experiments on 10 mobile phones show that the proposed RFF scheme yields 99.17% True Acceptance Rate (TAR) in real wireless environments. Experiments also show that the varying transmission power decreases the accuracy of RFF identification.

Radio Frequency Fingerprint Collaborative Intelligent Identification Using Incremental Learning

For distributed sensor systems using neural networks, each sub-network has a different electromagnetic environment, and these recognition accuracy is also different. In this paper, we propose a distributed sensor system using incremental learning to solve the problem of radio frequency fingerprint identification. First, the intelligent representation of the received signal is linearly fused into a four-channel image. Then, convolutional neural network is trained by using the existing data to obtain the preliminary model of the network, and decision fusion is used to solve the problem in the distributed system. Finally, using new data, instead of retraining the model, we employ incremental learning by fine-tuning the preliminary model. The proposed method can significantly reduce the training time and is adaptive to streaming data. Extensive experiments show that the proposed method is computationally efficient, and also has satisfactory recognition accuracy, especially at low signal-to-noise ratio (SNR) regime.

Conventional Neural Network-Based Radio Frequency Fingerprint Identification Using Raw I/Q Data

Radio frequency (RF) fingerprint identification is a nonpassword authentication method based on the physical layer of communication devices. Deep learning methods have thrown new light on RF fingerprint identification. In this paper, a conventional neural network- (CNN-) based RF identification model is proposed. The CNN models are designed to be lightweight. Raw data that reflects the characteristics of theIchannel, theQchannel, and the 2-dimensionalI+Qdata is successively fed into a CNN model. Therefore, three submodels are generated. The final predictive labels are determined by the results of the three submodels through a voting scheme. Experimental results have demonstrated that in the SNR setting at 5 dB, the final recognition accuracy of four transmit devices could achieve as high as 97.25%, while the identification accuracies based on theIchannel data,Qchannel data, andI+Qchannel data are 94.5%, 95%, and 94.5%, respectively. The training time for the 4 devices is around 30 seconds.

Research on combined radio frequency fingerprint identification model with limited samples

Aiming to solve the real problem of civilian aircraft identification, a novel combined radio frequency fingerprint (RFF) identification model is proposed, consisting of data analyzing processing, standard characteristic parameter database establishment, classification and optimization. In data analyzing processing step, discrimination was realized for wavelet coefficients, instantaneous phase, Hilbert huang transform energy spectrum, coefficients, time field envelope, probability density function, on basis of which, characteristic parameters were confirmed. In standard characteristic parameter database establishment step, a standard database was found through direct measurement method to avoid losing the RFF feature. In classification step, single character assortment rule and combined classifying rule were defined, with correlative concept and threshold concept. Finally, optimization for the model was realized by modifying parameters manually. Results show that, though hardware was limited and amount of samples were fewer, average identification rate is near to 69.75 percent, providing a theoretical reference for the real problem of identifying different aircrafts.

Radio Frequency Fingerprint-Based DSRC Intelligent Vehicle Networking Identification Mechanism in High Mobility Environment

In recent years, Dedicated Short-Range Communication (DSRC) vehicle interconnection technology has achieved mature development and broad applications, which is the key Vehicle to Everything (V2X) technology to realize transport intelligence. However, the openness of wireless transmission and the mobility of wireless terminals cause the identification mechanism of the DSRC system to face serious security threats. A radio frequency fingerprint (RFF)-based identification method can better resist the identity attack and spoofing by extracting the hardware characteristics formed by the differences of electronic components to authenticate different devices. Therefore, in this paper a novel RFF identification mechanism is proposed for IEEE 802.11p protocol-based DSRC intelligent vehicle networking devices suitable for a high mobility environment, in which the preamble field features of physical layer frames are extracted as device fingerprints, and the random forest algorithm and sequential detection method are used to distinguish and authenticate different devices. The experiment and simulation results demonstrate that the identification accuracy rates of the eight DSRC modules in the low-speed LOS and NLOS experimental states and up to 70 km/h high-speed simulations all exceed 99%, illustrating that this method has important application value in the field of identity authentication of V2X devices in high-speed scenarios.

Radio Frequency Fingerprint Identification Based on Slice Integration Cooperation and Heat Constellation Trace Figure

Radio frequency fingerprint (RFF) identification is a popular topic in the field of physical layer security. However, machine learning based RFF identification methods require complicated feature extraction manually while deep learning based methods are hard to achieve robust identification performance. To solve these problems, we propose a novel RFF identification method based on heat constellation trace figure (HCTF) and slice integration cooperation (SIC). HCTF is utilized to avoid the manual feature extraction and SIC is adopted to extract more features automatically in RF signals. Experimental results show that our proposed HCTF-SIC identification method can achieve higher accuracy than the existing RFF methods. The identification accuracy achieves 91.07% when SNR <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\pmb {=}$ </tex-math></inline-formula> 0 dB and it is even higher than 99.64% when the SNR <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\pmb {\ge }$ </tex-math></inline-formula> 5 dB.

Towards Scalable and Channel-Robust Radio Frequency Fingerprint Identification for LoRa

Radio frequency fingerprint identification (RFFI) is a promising device authentication technique based on transmitter hardware impairments. The device-specific hardware features can be extracted at the receiver by analyzing the received signal and used for authentication. In this paper, we propose a scalable and channel-robust RFFI framework achieved by deep learning powered radio frequency fingerprint (RFF) extractor and channel independent features. Specifically, we leverage deep metric learning to train an RFF extractor, which has excellent generalization ability and can extract RFFs from previously unseen devices. Any devices can be enrolled via the pre-trained RFF extractor and the RFF database can be maintained efficiently for allowing devices to join and leave. Wireless channel impacts the RFF extraction and is tackled by exploiting channel independent features and data augmentation. We carried out extensive experimental evaluation involving 60 commercial off-the-shelf LoRa devices and a USRP N210 software defined radio platform. The results have successfully demonstrated that our framework can achieve excellent generalization abilities for rogue device detection and device classification as well as effective channel mitigation.

Radio Frequency Fingerprint Identification Based on Logarithmic Power Cosine Spectrum

With the development of new Internet of Things (IoT) applications, such as unmanned ground vehicle (UGV), unmanned aerial vehicle (UAV), and unmanned surface vessel (USV), the security of wireless device identification is getting more and more attention. The radio frequency fingerprint (RFF) technology utilizes the unique hardware characteristics of the device for identity authentication, which overcomes the security risks of traditional authentication schemes based on distributable keys. In this paper, we propose an RFF identification scheme based on logarithmic power cosine spectrum for transient signals. We use the sliding window variance trajectory-based posterior probability density detection algorithm to improve the efficiency of transient signal detection, then adopt the discrete Fourier transform to extract the logarithmic envelope power spectrum of the transient signal, after that utilize the cosine transform to compresses the frequency domain features, and finally construct the 7-dimensional RFF feature vector. For the application scenario of USV, we acquire the radio frequency signals of 7 marine automatic identification systems (AIS) as the test dataset. The experimental results show that the proposed scheme can achieve ideal recognition accuracy using a Support Vector Machine as the classifier. Meanwhile, we use Principal Component Analysis to verify that the 7-dimensional RFF feature vector has good distinguishability for different wireless devices.

Radio frequency fingerprint identification based on stream differential constellation trace figures

Recently, radio frequency fingerprint (RFF) technique, characterized by unique hardware impairments, has seen vast attention for specific transmitter identification and authorized access. Differential constellation trace figure (DCTF) emerges as an effective image-based RFF method, which forms a stable constellation figure by performing a key differential process. Previous studies that are based on a single differential interval (DI) are susceptible to noise, which leads to under-performance in cases with low signal-to-noise ratios (SNRs). To address this problem, this paper proposes a stream DCTFs scheme that mainly consists of (i) RFF extraction deriving from numerous DIs, (ii) devising a feature reduction method containing feature importance ranking (FR) and feature set selection (FS), and (iii) extensive experimental evaluations. When the SNR ranges from 5 dB up to 10 dB, the classification results reach 96.3% and 98.4% respectively among 54 ZigBee devices, which are about 40% and 20% higher than existing DCTF-based methods. Moreover, the authentication accuracy reaches 100% in verification.

Radio Frequency Fingerprint Identification for LoRa Using Deep Learning

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 Fingerprint Identification for Narrowband Systems, Modelling and Classification

Device authentication is essential for securing Internet of things. Radio frequency fingerprint identification (RFFI) is an emerging technique that exploits intrinsic and unique hardware impairments as the device identifier. The existing RFFI literature focuses on experimental exploration but comprehensive modelling is missing. This paper systematically models impairments of transmitter and receiver in narrowband systems and carries out extensive experiments and simulations to evaluate their effects on RFFI. The modelled impairments include oscillator imperfections, imbalance of inphase (I) and quadrature (Q) branches of mixers and power amplifier (PA) nonlinearity. We then propose a convolutional neural network-based RFFI protocol. We carry out experimental measurements over three months and demonstrate that oscillator imperfections are not suitable for RFFI due to their unpredictable time variation caused by temperature change. Our simulation results show that our protocol can classify 50 and 200 devices with uniformly and randomly distributed IQ imbalances and PA nonlinearities with high accuracy, namely 99% and 89%, respectively. We also show that the RFFI has some tolerance on different receiver imbalances during training and classification. Specifically, the accuracy is shown to degrade less than 20% when the residual receiver's gain and phase imbalances are small. Based on the experimental and simulation results, we made recommendations for designing a robust RFFI protocol, namely compensate carrier frequency offset and calibrate IQ imbalances of receivers.

Differential Contour Stellar-Based Radio Frequency Fingerprint Identification for Internet of Things

Data attacks from illegal access devices of the Internet of Things will cause serious interference and threats to the entire network. It is difficult to ensure the security of the communication system only by relying on traditional application layer password authentication methods. Therefore, it is of great significance to design an effective physical layer authentication system based on radio frequency fingerprints. Regarding the issue above, this paper proposes a novel physical layer authentication method for Internet of Things based on differential contour stellar. Through the test of identification and authentication of 20 WiFi network card devices from same manufacturer, same type and same batch, the recognition accuracy rate can reach 98.6% by the proposed method. The proposed method can improve the effect of radio frequency fingerprint identification from three aspects: i. The differential processing can effectively reduce the negative influence of phase rotation caused by carrier frequency offset and Doppler effects; ii. The color processing can effectively reduce the negative influence of random noise caused by channel noise; iii. It is suitable for processing large-scale networks and the massive data they bring.

Radio frequency fingerprinting identification for Zigbee via lightweight CNN

Zigbee is a popular communication protocol in the Internet of things (IoT) which shows great potential in smart home. However, the smart device has the risk of being hijacked by unauthorized users and may result in privacy disclosure. Traditional device identification is based on cryptography which is easy to be cracked. Recently, radio frequency fingerprinting identification (RFFID) is popular in device identification. Traditional RFFID’s power consumption and cost is unacceptable to Zigbee. In order to reduce the cost, more effective model can be used to reduce the number of neurons. This paper proposes a RFFID method based on lightweight convolution neural network (CNN) which can adopt low power consumption and cost. The simulation result shows that this method can identification Zigbee device, and the accuracy reached 100%. Also, the parameter has reduced to about 93%.

Joint multislice and cooperative detection aided RFID method based on deep learning

Radio frequency fingerprint identification (RFID) provokes many promising applications of internet of things. Deep learning is considered as one of powerful tools to empower RFID techniques. Recently, several deep learning based RFID methods have been proposed. However, their deep neural networks were trained from the limited length of RF fingerprint samples due to the very high training cost. Hence, existing deep learning based RFID methods are hard to extract full features from the RF fingerprint (RFF) datasets. In order to solve this problem, we propose a joint multislice and cooperative detection aided RFID method based on deep learning. Firstly, acquisition equipment is used to collect RFF signals from seven power amplifiers, which are composed of in-phase and quadrature (IQ) samples with 200,000 sampling points. The IQ samples are sliced and turned into slices with fewer sampling points, which makes them use less training resources, and then they are input into neural network for training. The convolutional neural network (CNN) and convolutional long short-term deep neural networks (CLDNN) are used for training. Secondly, a cooperative detection algorithm is proposed to classify all slices from the same signal to determine the signal category. Finally, experiment results are given to confirm the proposed method in different scenarios. It shows that this method can greatly reduce the training resources, and at the same time maintain a high accuracy.

Radio Frequency Fingerprint Identification Based on Deep Complex Residual Network

Radio frequency fingerprint identification is a non-password authentication method based on the physical layer hardware of the communication device. Deep learning methods provide new ideas and techniques for radio frequency fingerprint identification. As a bridge between electromagnetic signal recognition and deep learning, the electromagnetic signal recognition method based on statistical constellation still needs to go through data preprocessing and feature engineering, which is contrary to the end-to-end learning method emphasized by deep learning. Moreover, in the process of converting electromagnetic signal waveform data into images, there is inevitably information loss. Establishing a universal radio frequency fingerprint recognition model suitable for wireless communication scenarios is not only conducive to optimizing the communication system, but also can reduce the cost and time of model selection. Therefore, how to design a deep learning radio frequency fingerprint recognition model suitable for wireless communication is an important problem for researchers. Aiming at the problem that the existing radio frequency fingerprint extraction and identification methods have low recognition rate of communication radiation source individuals, a radio frequency fingerprint identification method based on deep complex residual network is proposed. Through the deep complex residual network, the radio frequency fingerprint feature extraction of the communication radiation source individual is integrated with the recognition process, and an end-to-end deep learning model suitable for wireless communication is established, which greatly improves the identification accuracy of the communication radiation source individuals compared with typical constellation based methods.