IET Communications最新文献

Specific emitter identification technology plays a very important role in spectrum resource management, wireless network security, cognitive radio etc. However, in complex electromagnetic environments, the variability and uncertainty of signals make it very difficult to extract representative feature representations of the signals. At the same time, the feature extraction capability of the recognition model is also a factor that needs to be considered. To address these issues, a wavelet residual neural network model based on attention mechanism is proposed for specific emitter identification. First, multi-level wavelet decomposition is performed on all received signals to obtain their wavelet detail coefficients at different scales. Next, all the wavelet detail coefficients are used as the feature input for the attention-based residual network, and perform parallel feature extraction at multi scales. Finally, the feature representation capability of all coefficients are compared, and the model's recognition results based on it are obtained. The recognition rates on the three datasets are 94.7%, 93.21%, and 86.1%, respectively, all of which are superior to recent state-of-the-art algorithms. In addition, through ablation experiment, the validity of each component of the model has been verified.

In present times, Radio-Frequency Identification (RFID) systems have seen a significant rise in their usage. There has been an increasing interest in developing even lighter RFID protocols suitable for resource-constrained environments. Ensuring security and privacy remain critical challenges in RFID-based systems. Recently proposed lightweight authentication schemes, namely LRSAS+ and LRARP+, are ideally suited for constrained devices. However, this article investigates these schemes and reveals certain vulnerabilities: LRSAS+ is susceptible to tag impersonation, desynchronization, and traceability attacks, while LRARP+ can fall prey to traceability and secret disclosure attacks. An enhanced version of these authentication systems is proposed that tackles their inherent weaknesses by leveraging the $��\chi �p�e�r�$ function. To verify the security of the proposed scheme, a formal analysis is conducted using Gong–Needham–Yahalom logic (GNY logic) and an automated security protocol verification tool, ProVerif. The improved scheme's effectiveness is also compared with multiple contemporary lightweight systems. The results indicate that the enhanced scheme not only meets the security requirements for lightweight authentication schemes but also achieves this with minimal computational overhead.

Within the evolving landscape of fifth-generation (5G) wireless networks, the introduction of network-slicing protocols has become pivotal, enabling the accommodation of diverse application needs while fortifying defences against potential security breaches. This study endeavours to construct a comprehensive network-slicing model integrated with an attack detection system within the 5G framework. Leveraging software-defined networking (SDN) along with deep learning techniques, this approach seeks to fortify security measures while optimizing network performance. This undertaking introduces network slicing predicated on SDN with the OpenFlow protocol and Ryu control technology, complemented by a neural network model for attack detection using deep learning methodologies. Additionally, the proposed convolutional neural networks-long short-term memory approach demonstrates superiority over conventional ML algorithms, signifying its potential for real-time attack detection. Evaluation of the proposed system using a 5G dataset showcases an impressive accuracy of 99%, surpassing previous studies, and affirming the efficacy of the approach. Moreover, network slicing significantly enhances quality of service by segmenting services based on bandwidth. Future research will concentrate on real-world implementation, encompassing diverse dataset evaluations, and assessing the model's adaptability across varied scenarios.

Deep learning-based models have become ubiquitous across a wide range of applications, including computer vision, natural language processing, and robotics. Despite their efficacy, one of the significant challenges associated with deep neural network (DNN) models is the potential risk of copyright leakage due to the inherent vulnerability of the entire model architecture and the communication burden of the large models during publishing. So far, it is still challenging for us to safeguard the intellectual property rights of these DNN models while reducing the communication time during model publishing. To this end, this paper introduces a novel approach using knowledge distillation techniques aimed at training a surrogate model to stand in for the original DNN model. To be specific, a knowledge distillation generative adversarial network (KDGAN) model is proposed to train a student model capable of achieving remarkable performance levels while simultaneously safeguarding the copyright integrity of the original large teacher model and improving communication efficiency during model publishing. Herein, comprehensive experiments are conducted to showcase the efficacy of model copyright protection, communication-efficient model publishing, and the superiority of the proposed KDGAN model over other copyright protection mechanisms.

The challenge of ensuring reliability for high-efficiency technology, multiple-input-multiple-output orthogonal-frequency-division-multiplexing (MIMO-OFDM), in wireless frequency-selective fading environments persists. In this article, the concept of spreading a symbol's energy is proposed as a viable solution to enhance transmission reliability for MIMO-OFDM systems. And an energy-spreading-transform (EST)-based MIMO-OFDM transceiver is developed. Following the Inverse Fast Fourier Transform (IFFT) performed by the conventional MIMO-OFDM transmitter, an orthogonal transformation called the EST is introduced. This transform spreads the energy of a symbol across the entire frequency domain and all time slots. The EST is coupled with the improved iterative detection algorithm named EST-partial decision (PD)-iterative-interference-cancellation (EST-PD-IIC) to maximize and leverage the potential diversity gain. Numerical simulation results demonstrate that the proposed scheme approaches the performance bound when signal-to-noise ratio (SNR) is about 21dB for 16-ary quadrature amplitude modulation (16-QAM). Complexity analysis illustrates that the computational complexity of the evolved EST-PD-IIC algorithm is lower than that of the famous vertically Bell laboratory layered space-time detector (V-BLAST) when the antenna array size is greater than $��3�\times �3�$. In summary, the proposed scheme is practical for providing high-quality communication in multi-path fading environments and can even enable a reliable communication without channel encoding when Eb/N0 exceeds a threshold in 5G-Advanced.

The Network Function Virtualization (NFV) technology has emerged to turn hardware-based network functions into software-based virtual entities. In NFV-enabled multicast services, the data flow should be passed through a series of Virtual Network Functions (VNFs) before reaching destinations. In the problem of NFV-enabled multicast service embedding, not only the VNFs must be deployed, but also the traffic forwarding topology must be constructed. As the exact solution of this problem suffers from high computational complexity, the heuristic or approximation approaches are used in practice. However, as a way to control the trade off between complexity and efficiency, using multistage solutions is offered in literature. In this article, some two-stage approaches for embedding NFV-enabled multicast services are introduced, and they are compared through analysis and simulation. Specifically, a new low-complexity approach based on the Auxiliary VNF Graph (AVG) is proposed to determine the sub-optimal locations for VNF placement and to construct the NFV-based multicast routing tree. The comparative analysis shows that the proposal has acceptable performance while reducing the computational complexity significantly.

Automatic modulation classification models based on deep learning models are at risk of being interfered by adversarial attacks. In an adversarial attack, the attacker causes the classification model to misclassify the received signal by adding carefully crafted adversarial interference to the transmitted signal. Based on the requirements of efficient computing and edge deployment, a lightweight automatic modulation classification model is proposed. Considering that the lightweight automatic modulation classification model is more susceptible to interference from adversarial attacks and that adversarial training of the lightweight auto-modulation classification model fails to achieve the desired results, an adversarial attack defense system for the lightweight automatic modulation classification model is further proposed, which can enhance the robustness when subjected to adversarial attacks. The defense method aims to transfer the adversarial robustness from a trained large automatic modulation classification model to a lightweight model through the technique of adversarial robust distillation. The proposed method exhibits better adversarial robustness than current defense techniques in feature fusion based automatic modulation classification models in white box attack scenarios.

Communication systems are greatly hampered by many disruptive noises in powerline communication systems (PLC), which come with strong interference, resulting in the malfunction of PLC systems. Hence, there is a need to model noise and its effect on communication systems. This paper presents noise modelling and mitigation techniques for indoor broadband powerline communication systems. To model the PLC noise, frequency domain measurements employing the GSP-930 spectrum analyser were carried out to determine the noise frequency response in the frequency range of 1–30 MHz. The results obtained were plotted. While the analytical model for the noise model is presented, furthermore, noise mitigation techniques for multiple input multiple output PLC (MIMO-PLC) systems in the form of spatial modulation PLC systems have been proposed. The SM-PLC system employs the indices of the individual transmit lines to increase the data rate, as opposed to the traditional MIMO-PLC systems, where the symbol to be transmitted is transmitted by duplicating the symbol across all lines. The proposed system uses the maximum likelihood (ML) detector at the receiver to obtain estimates of the transmitted symbols. The simulation results of the SM-PLC system are compared with the already existing MIMO-PLC system and show a significant improvement of ≈6 dB and 5.2 dB in signal-to-noise ratio (SNR) at a bit error rate of 10(−5) for spectral efficiencies of 4 bits per channel use (bpcu) and 6 bpcu, respectively. On comparison of the SM-PLC system having a combination of additive white Gaussian noise and impulse noise at the receiver, the SM-PLC system outperformed the traditional MIMO-PLC by 3.5 and 3.8 dB in SNR for 4 and 6 bpcu, respectively.

Intelligent reflecting surface (IRS) has recently been considered as a potential technology for realizing ultra-reliable and low-latency (URLLC) in wireless networks. This paper proposes a resource optimization scheme to maximize the sum-rate for an IRS-assisted downlink multiuser multi-input single-output (MISO) URLLC system. For the perfect CSI scenario, we jointly optimize each user's block-length and packet-error probability, the precoding vectors at the base station (BS), and the passive beamforming with discrete phase shifts at the IRS. Given the problem's complexity, we design a computationally efficient iterative algorithm using successive convex approximation (SCA) and semidefinite relaxation (SDR) techniques to obtain a locally optimal solution. Specifically, for the imperfect CSI scenario, we construct a robust resource optimization problem model and incorporate the S-procedure to address the impact of channel uncertainty, proposing an iterative algorithm based on the alternating optimization (AO) method to achieve a locally optimal solution. Simulation results demonstrate that: 1) An IRS equipped with a 2-bit quantized resolution phase shifter is sufficient to achieve a system sum-rate comparable to that of an ideal phase shifter; 2) Compared to other Baseline schemes, Algorithm 2 exhibits better robustness and superior performance gains under imperfect CSI.