Specific emitter identification (SEI) is a technique that distinguishes between unique emitters using the external feature measurements from their transmit signals, primarily radio frequency fingerprints. SEI has been widely adopted for military and civilian spectrum management applications. We propose a deep-learning based SEI approach that uses the features of the received steady-state signals. In particular, the bispectrum of the received signal is calculated as a unique feature. Then, we use a supervised dimensionality reduction method to significantly reduce the dimensions of the bispectrum. Finally, a convolutional neural network is adopted to identify specific emitters using the compressed bispectrum. This approach essentially extracts overall feature information hidden in the original signals, which can then be used to improve identification performance. Results from both the simulations and the software radio experiments are provided. A signal acquisition system is designed to collect steady-state signals from multiple universal software radio peripherals (USRPs). Both the simulations and the experiments validate our conclusion that the proposed approach outperforms other existing schemes in the literature.

In this paper, we investigate the specific emitter identification (SEI) problem, which distinguishes different emitters using features generated by the nonlinearity of the power amplifiers of emitters. SEI is performed by measuring the features representing the individual specifications of emitters and making a decision based on their differences. In this paper, the SEI problem is considered in both single-hop and relaying scenarios, and three algorithms based on the Hilbert spectrum are proposed. The first employs the entropy and the first- and second-order moments as identification features, which describe the uniformity of the Hilbert spectrum. The second uses the correlation coefficient as an identification feature, by evaluating the similarity between different Hilbert spectra. The third exploits Fisher's discriminant ratio to obtain the identification features by selecting the Hilbert spectrum elements with strong class separability. When compared with the existing literature, we further consider the identification problem in a relaying scenario, in which the fingerprint of different emitters is contaminated by the relay's fingerprints. Moreover, we explore the identification performance under various channel conditions, such as additive white Gaussian noise, non-Gaussian noise, and fading. Extensive simulation experiments are performed to evaluate the identification performance of the proposed algorithms, and results show their effectiveness in both single-hop and relaying scenarios, as well as under different channel conditions.

A new approach to modulation classification based on the Kolmogorov-Smirnov (K-S) test is proposed. The K-S test is a non-parametric method to measure the goodness of fit. The basic procedure involves computing the empirical cumulative distribution function (ECDF) of some decision statistic derived from the received signal, and comparing it with the CDFs or the ECDFs of the signal under each candidate modulation format. The K-S-based modulation classifiers are developed for various channels, including the AWGN channel, the flat-fading channel, the OFDM channel, and the channel with unknown phase and frequency offsets, as well as the non-Gaussian noise channel, for both QAM and PSK modulations. Extensive simulation results demonstrate that compared with the traditional cumulant-based classifiers, the proposed K-S classifiers offer superior classification performance, require less number of signal samples (thus is fast), and is more robust to various channel impairments.

Specific emitter identification (SEI) is a technique that identifies the unique emitter from its received signal by using the specific characteristics of an emitter. In this paper, we consider an SEI problem with unknown receiver distortion. Two groups of SEI schemes based on signal decomposition are proposed. In the proposed schemes, the received signal is pre-processed by either of the following decomposition, i.e., empirical mode decomposition (EMD), intrinsic time-scale decomposition (ITD), or variational mode decomposition (VMD). In the first group of the proposed schemes, the skewness and the kurtosis are extracted from the decomposed signal, which characterize the non-Gaussian features of the signal. The support vector machine (SVM) or the back-propagation (BP) neural network is applied to fuse the features extracted from the multiple distorted receivers respectively and then determine the unknown emitter. In the second group of the proposed schemes, an approach based on the long short term memory (LSTM) is proposed. The LSTM model learns the deep features rather than the specific non-Gaussian features from the pre-processed signal. In contrast to the first group, the features used to identify the unknown emitter are extracted directly from the pre-processed signal by the trained LSTM model. Simulation results show that the proposed multi-receiver cooperative schemes can achieve the diversity gain in the identification performance. Moreover, we evaluate the identification performance of the proposed schemes in various channels, including the Gaussian channel and the fading channel. Compared to the existing methods based on different time-frequency representations, the proposed schemes possess the merits of high identification accuracy and low complexity. The significance of this paper is that the receive diversity can be achieved by the proposed schemes by using multiple distorted receivers even without compensating the receiver distortion prior to the identification.

In this paper, we investigate the artificial noise-aided jamming design for a transmitter equipped with large antenna array in Rician fading channels. We figure out that when the number of transmit antennas tends to infinity, whether the secrecy outage happens in a Rician channel depends on the geometric locations of eavesdroppers. In this light, we first define and analytically describe the secrecy outage region (SOR), indicating all possible locations of an eavesdropper that can cause secrecy outage. After that, the secrecy outage probability (SOP) is derived, and a jamming-beneficial range, i.e., the distance range of eavesdroppers which enables uniform jamming to reduce the SOP, is determined. Then, the optimal power allocation between messages and artificial noise is investigated for different scenarios. Furthermore, to use the jamming power more efficiently and further reduce the SOP, we propose directional jamming that generates jamming signals at selected beams (mapped to physical angles) only, and power allocation algorithms are proposed for the cases with and without the information of the suspicious area, i.e., possible locations of eavesdroppers. We further extend the discussions to multiuser and multi-cell scenarios. At last, numerical results validate our conclusions and show the effectiveness of our proposed jamming power allocation schemes.

Integrated sensing and communication (ISAC), and intelligent reflecting surface (IRS) are envisioned as revolutionary technologies to enhance spectral and energy efficiencies for next wireless system generations. For the first time, this paper focuses on the channel estimation problem in an IRS-assisted ISAC system. This problem is challenging due to the lack of signal processing capacity in passive IRS, as well as the presence of mutual interference between sensing and communication (SAC) signals in ISAC systems. A three-stage approach is proposed to decouple the estimation problem into sub-ones, including the estimation of the direct SAC channels in the first stage, reflected communication channel in the second stage, and reflected sensing channel in the third stage. The proposed three-stage approach is based on a deep-learning framework, which involves two different convolutional neural network (CNN) architectures to estimate the channels at the full-duplex ISAC base station. Furthermore, two types of input-output pairs to train the CNNs are carefully designed, which affect the estimation performance under various signal-to-noise ratio conditions and system parameters. Simulation results validate the superiority of the proposed estimation approach compared to the least-squares baseline scheme, and its computational complexity is also analyzed.