Accurate waveform identification, especially at low SNRs, remains an open challenge; both classical hypothesis-test detectors and modern deep neural networks degrade sharply as SNR falls. We address this with a graph-neural approach that converts each noisy in-phase/quadrature (IQ) segment into a multi-scale temporal graph: every sample becomes a node linked to neighbors at multiple lags (±1,±2,±4,±8) and to feature-space k-nearest neighbors. Each node carries a six-channel feature vector $\left[ {I,Q,|x|,\phi ,\delta \phi ,|x{|^2}} \right]$ designed to surface subtle patterns masked by noise. A hybrid CNN-GNN then performs classification: a 1D convolutional front-end learns local temporal embeddings, followed by a deep residual GNN with interleaved GCN and GATv2 layers to propagate information over the graph. We use Jumping Knowledge (JK) aggregation to preserve multi-hop and shallow cues, and an attention-based readout to emphasize the most informative nodes. On a synthetic four-class dataset (LTE, 5G NR, Radar, noise) at −10dB average SNR, the proposed model attains 91.3% test accuracy, exceeding strong baselines. This demonstrates substantial performance gains over conventional CNNs and deep learning classifiers in the low-SNR regime.

Interference is one of the most critical issues in the cellular Device-to-Device (D2D) networks. The sharing of radio resources in cellular and D2D communications offers spectrum efficiency advantages for the cellular network. However, resource sharing also introduces interference, leading to a reduction in the quality of service experienced by users. In this paper, we propose an adversarial Multi-Armed Bandit learning-based transmission Power Control method called MAB-PC for both cellular and D2D transmitters. The objective of this method is to ensure the minimum service quality for users, considering the minimum spectral efficiency and maximum block error rate. Additionally, to address the conflicting objectives of D2D and cellular communications, MAB-PC is modeled as a Pareto optimization problem for D2D transmitters. MAB-PC is a distributed method that minimizes signaling overhead and relies solely on local Channel State Information (CSI). The effectiveness of the proposed method is evaluated based on reliability, total data rate, spectral efficiency, block error rate, and outage probability, demonstrating superior performance compared to its counterpart.

Covert channel is one of the most interesting topics in the computer networks security. Covert channel designers are seeking to discover weaknesses in the communications algorithms to use them as the medium for covert transmission. Broadcast nature of wireless channels has provided a favorable environment for the design of the hidden channels. CSMA/CA is used to control channel access in IEEE 802.11 network. Random features of this algorithm can be used to create timing covert channel. The statistical distribution of the free time intervals' duration is used in this paper for covert channel establishment. Hidden messages are sent via manipulating the timing of the overt packets' transmission. Hidden transceiver senses the wireless channel continuously to be adapted to the dynamic network condition and to be less detectable. To increase the covert channel's accuracy, some free interval durations are not used that leads to security degradation. This problem is also covered by a gap covering method that is based on the summation of the channel sensed free time interval distribution and a normal one. Hidden nodes also estimate the number of active nodes and adapt their behavior accordingly to keep their compatibility with the network. The statistical Kolmogorov–Smirnov and regularity tests are used to assess the security of the covert channel. Simulation results show that the proposed covert channel have a high bit rate along with high security. © 2016 The Authors Security and Communication Networks published by John Wiley & Sons Ltd

A new end-point admission control algorithm is proposed. The proposed algorithm helps to manage the network traffic within a domain more efficiently in the next generation network where multiple classes of service are required by different applications. In the existing solutions, when a request for a new traffic is received by the network, according to the admission control mechanism the availability of resources for the requested service class is examined and the call is accepted if the resources are available. In the proposed algorithm, users' are allowed to temporarily use lower service classes in the routers along the path, whenever the requested service class is not available, given that the end-to-end service quality level is preserved unless a lower service quality is acceptable by the application. The probe-based end-point admission control mechanism proposed here, dynamically manages the available bandwidth. In this way more calls can be admitted and the utilisation of the network is increased.