In this paper, the physical layer secure transmission in multi-antenna multi-user cognitive internet-of-thing (IoT) network is investigated, where the coalitional game based joint beamforming and power control scheme is proposed to improve the achievable security of cognitive IoT devices. Specifically, the secondary network consisting of a muti-antenna secondary transmitter, multiple secondary users (SUs), is allowed to access the licensed spectrum resource of primary user (PU) with underlay approach in the presence of an unauthorized eavesdropper. Based on the Merge-Split-Rule, coalitional game is formulated among distributed secondary users with cooperative receive beamforming. Then, an alternative optimization method is used to obtain the optimized beamforming and power allocation schemes by applying the up-downlink duality. The simulation results demonstrate the effectiveness of our proposed scheme in improving the SU's secrecy rate and system utility while guaranteeing PU's interference threshold.

This paper studies the proactive spectrum monitoring with one half-duplex spectrum monitor (SM) to cope with the potential suspicious wireless powered communications (SWPC) in dynamic spectrum sharing networks. The jamming-assisted spectrum monitoring scheme via spectrum monitoring data (SMD) transmission is proposed to maximize the sum ergodic monitoring rate at SM. In SWPC, the suspicious communications of each data block occupy multiple independent blocks, with a block dedicated to the wireless energy transfer by the energy-constrained suspicious nodes with locations in a same cluster (symmetric scene) or randomly distributed (asymmetric scene) and the remaining blocks used for the information transmission from suspicious transmitters (STs) to suspicious destination (SD). For the symmetric scene, with a given number of blocks for SMD transmission, namely the jamming operation, we first reveal that SM should transmit SMD signal (jam the SD) with tolerable maximum power in the given blocks. The perceived suspicious signal power at SM could be maximized, and thus so does the corresponding sum ergodic monitoring rate. Then, we further reveal one fundamental trade-off in deciding the optimal number of given blocks for SMD transmission. For the asymmetric scene, a low-complexity greedy block selection scheme is proposed to guarantee the optimal performance. Simulation results show that the jamming-assisted spectrum monitoring schemes via SMD transmission achieve much better performance than conventional passive spectrum monitoring, since the proposed schemes can obtain more accurate and effective spectrum characteristic parameters, which provide basic support for fine-grained spectrum management and a solution for spectrum security in dynamic spectrum sharing network.

Cloud-based satellite and terrestrial spectrum shared networks (CB-STSSN) combines the triple advantages of efficient and flexible network management of heterogeneous cloud access (H-CRAN), vast coverage of satellite networks, and good communication quality of terrestrial networks. Thanks to the complementary coverage characteristics, anytime and anywhere high-speed communications can be achieved to meet the various needs of users. The scarcity of spectrum resources is a common problem in both satellite and terrestrial networks. In order to improve resource utilization, the spectrum is shared not only within each component but also between satellite beams and terrestrial cells, which introduces inter-component interferences. To this end, this paper first proposes an analytical framework which considers the inter-component interferences induced by spectrum sharing (SS). An intelligent SS scheme based on radio map (RM) consisting of LSTM-based beam prediction (BP), transfer learning-based spectrum prediction (SP) and joint non-preemptive priority and preemptive priority (J-NPAP)-based proportional fair spectrum allocation is than proposed. The simulation result shows that the spectrum utilization rate of CB-STSSN is improved and user blocking rate and waiting probability are decreased by the proposed scheme.

The spectrum sensing model based on deep learning has achieved satisfying detection performence, but its robustness has not been verified. In this paper, we propose primary user adversarial attack (PUAA) to verify the robustness of the deep learning based spectrum sensing model. PUAA adds a carefully manufactured perturbation to the benign primary user signal, which greatly reduces the probability of detection of the spectrum sensing model. We design three PUAA methods in black box scenario. In order to defend against PUAA, we propose a defense method based on autoencoder named DeepFilter. We apply the long short-term memory network and the convolutional neural network together to DeepFilter, so that it can extract the temporal and local features of the input signal at the same time to achieve effective defense. Extensive experiments are conducted to evaluate the attack effect of the designed PUAA method and the defense effect of DeepFilter. Results show that the three PUAA methods designed can greatly reduce the probability of detection of the deep learning-based spectrum sensing model. In addition, the experimental results of the defense effect of DeepFilter show that DeepFilter can effectively defend against PUAA without affecting the detection performance of the model.

Specific emitter identification can distinguish individual transmitters by analyzing received signals and extracting inherent features of hard-ware circuits. Feature extraction is a key part of traditional machine learning-based methods, but manual extraction is generally limited by prior professional knowledge. At the same time, it has been noted that the performance of most specific emitter identification methods degrades in the low signal-to-noise ratio (SNR) environments. The deep residual shrinkage network (DRSN) is proposed for specific emitter identification, particularly in the low SNRs. The soft threshold can preserve more key features for the improvement of performance, and an identity shortcut can speed up the training process. We collect signals via the receiver to create a dataset in the actual environments. The DRSN is trained to automatically extract features and implement the classification of transmitters. Experimental results show that DRSN obtains the best accuracy under different SNRs and has less running time, which demonstrates the effectiveness of DRSN in identifying specific emitters.

In spectrum sharing systems, locating multiple radiation sources can efficiently find out the intruders, which protects the shared spectrum from malicious jamming or other unauthorized usage. Compared to single-source localization, simultaneously locating multiple sources is more challenging in practice since the association between measurement parameters and source nodes are not known. Moreover, the number of possible measurements-source associations increases exponentially with the number of sensor nodes. It is crucial to discriminate which measurements correspond to the same source before localization. In this work, we propose a centralized localization scheme to estimate the positions of multiple sources. Firstly, we develop two computationally light methods to handle the unknown RSS-AOA measurements-source association problem. One method utilizes linear coordinate conversion to compute the minimum spatial Euclidean distance summation of measurements. Another method exploits the long-short-term memory (LSTM) network to classify the measurement sequences. Then, we propose a weighted least squares (WLS) approach to obtain the closed-form estimation of the positions by linearizing the non-convex localization problem. Numerical results demonstrate that the proposed scheme could gain sufficient localization accuracy under adversarial scenarios where the sources are in close proximity and the measurement noise is strong.

The continuous change of communication frequency brings difficulties to the reconnaissance and prediction of non-cooperative communication networks. Since the frequency-hopping (FH) sequence is usually generated by a certain model with certain regularity, the FH frequency is thus predictable. In this paper, we investigate the FH frequency reconnaissance and prediction of a non-cooperative communication network by effective FH signal detection, time-frequency (TF) analysis, wavelet detection and frequency estimation. With the intercepted massive FH signal data, long short-term memory (LSTM) neural network model is constructed for FH frequency prediction. Simulation results show that our parameter estimation methods could estimate frequency accurately in the presence of certain noise. Moreover, the LSTM-based scheme can effectively predict FH frequency and frequency interval.

Cognitive Internet of Things (IoT) has attracted much attention due to its high spectrum utilization. However, potential security of the shortpacket communications in cognitive IoT becomes an important issue. This paper proposes a relay-assisted maximum ratio combining/zero forcing beamforming (MRC/ZFB) scheme to guarantee the secrecy performance of dual-hop short-packet communications in cognitive IoT. This paper analyzes the average secrecy throughput of the system and further investigates two asymptotic scenarios with the high signal-to-noise ratio (SNR) regime and the infinite blocklength. In addition, the Fibonacci-based alternating optimization method is adopted to jointly optimize the spectrum sensing blocklength and transmission blocklength to maximize the average secrecy throughput. The numerical results verify the impact of the system parameters on the tradeoff between the spectrum sensing blocklength and transmission blocklength under a secrecy constraint. It is shown that the proposed scheme achieves better secrecy performance than other benchmark schemes.

with the development of 5G, the future wireless communication network tends to be more and more intelligent. In the face of new service demands of communication in the future such as super-heterogeneous network, multiple communication scenarios, large number of antenna elements and large bandwidth, new theories and technologies of intelligent communication have been widely studied, among which Deep Learning (DL) is a powerful technology in artificial intelligence(AI). It can be trained to continuously learn to update the optimal parameters. This paper reviews the latest research progress of DL in intelligent communication, and emphatically introduces five scenarios including Cognitive Radio (CR), Edge Computing (EC), Channel Measurement (CM), End to end Encoder/Decoder (EED) and Visible Light Communication (VLC). The prospect and challenges of further research and development in the future are also discussed.