Unmanned aerial vehicle (UAV)-assisted non-orthogonal multiple access (NOMA) satellite Internet of Things (IoT) networks face severe physical-layer security challenges in the presence of eavesdroppers. To address this issue, this paper proposes a secure graph neural network (Sec-GNN) based multi-dimensional anti-eavesdropping optimization method. The approach models the node-spatial relationships among the UAV, legitimate users, and eavesdroppers as a graph structure. By leveraging the message-passing mechanism of graph neural networks—sequently performing message generation, message aggregation, and node update—it dynamically integrates network topology information and node interaction features. This enables end-to-end joint optimization of the UAV’s three-dimensional position, beamforming vectors, and multi-user power allocation strategies. The method does not rely on explicit channel state information and directly generates near-optimal resource allocation schemes based on node location information and observable signal features. Experimental results demonstrate the superiority of Sec-GNN across various scenarios, and ablation studies confirm that partial optimization leads to significant performance degradation, thereby verifying the necessity of multi-dimensional joint design. The proposed framework provides an efficient and scalable solution for secure resource management in dynamic space-air-ground integrated networks.

Intelligent Reflecting Surfaces (IRS) enhance spectral efficiency by adjusting reflection phase shifts, while Non-Orthogonal Multiple Access (NOMA) increases system capacity. Consequently, IRS-assisted NOMA communications have garnered significant research interest. However, the passive nature of the IRS, lacking authentication and security protocols, makes these systems vulnerable to external eavesdropping due to the openness of electromagnetic signal propagation and reflection. NOMA’s inherent multi-user signal superposition also introduces internal eavesdropping risks during user pairing. This paper investigates secure transmissions in IRS-assisted NOMA systems with heterogeneous resource configuration in wireless networks to mitigate both external and internal eavesdropping. To maximize the sum secrecy rate of legitimate users, we propose a combinatorial optimization graph neural network (CO-GNN) approach to jointly optimize beamforming at the base station, power allocation of NOMA users, and phase shifts of IRS for dynamic heterogeneous resource allocation, thereby enabling the design of dual-link or multi-link secure transmissions in the presence of eavesdroppers on the same or heterogeneous links. The CO-GNN algorithm simplifies the complex mathematical problem-solving process, eliminates the need for channel estimation, and enhances scalability. Simulation results demonstrate that the proposed algorithm significantly enhances the secure transmission performance of the system.

Relay and friendly interference collaboration are effective technologies within the physical layer security (PLS) domain for countering eavesdroppers in wireless transmissions. However, the dynamic nature of wireless channels means that the quality of legitimate channels may not consistently exceed that of eavesdropping channels, posing challenges in ensuring the security performance of wireless links. In this paper, we present a multi-destination node selection framework aimed at enhancing the security of wireless communication systems. The strategic selection of relays, in conjunction with the deployment of friendly interference, is designed to optimize the reliability and secrecy performance of wireless link transmissions. Specifically, we propose a collaboration-based node selection (CNS) strategy that leverages selection combining (SC) and maximal ratio combining (MRC) to enhance system reliability and security. Through theoretical analysis, we derive closed-form expressions for secrecy capacity, outage probability (OP), intercept probability (IP), and asymptotic outage probability. The simulation results validate our analytical conclusions and demonstrate the effectiveness of the CNS scheme. Importantly, the introduction of interference nodes strengthens system security and reliability, while increasing relays or destinations primarily optimizes system robustness.

In order to improve the signal‐to‐noise ratio (SNR) gain and lower the bit error rate (BER) when a weak signal is buried in the noise, the parameter‐tuned stochastic resonator (PSR) is studied in more detail. In this study, the authors explore the impact of the number of branches on performance. Hence, they build the parameter‐tuned bistable parallel array system, which consists of a group of PSRs and propose a novel method to derive the probability density function (PDF) of the output signal, which combines the conventional PDF based on the approximation theory with Gaussian distribution. Based on this method, an analytical expression for BER of the system is derived. It is of interest to note that for an input binary pulse amplitude modulation signal buried in noise, the weak signal can be detected by using the parameter‐tuned bistable parallel array system. It is found that via the array PSR effect, the system output SNR gain can be improved. Moreover, the BER can also be reduced with the increase of the array size as the array size increases.

Bistable parallel array system can efficiently improve the signal‐to‐noise ratio (SNR) gain and further significantly lower bit‐error‐rate (BER) when the SNR is low. The bistable parallel array system is widely studied due to its outstanding advantages. This study presents a new method that applies combining techniques including maximum ratio combining (MRC), equal gain combining (EGC), and selection combining (SC) to the bistable parallel array system, and derives the formulas of the SNR gain, energy efficiency, and numerically calculates the BER. Through comparative analysis of these three combining techniques, it demonstrates the BER performance of the EGC technique in bistable parallel array system slightly inferiors to MRC, and the worst is SC. While the performance of all these three kinds of combining techniques is better than that of the single branch case. Importantly, higher SNR gain, higher EE and lower BER can be obtained in non‐Gaussian noise cases than that in Gaussian noise cases.

To boost the performance of binary pulse amplitude modulation at low signal‐to‐noise ratio, the parameter‐tuned stochastic resonance (SR) is introduced into digital communications system. In this study, an analytical framework is developed for evaluating the system performance by approximating the probability density function of the Ornstein–Uhlebeck noise based on the central limit theorem. Expression for the bit error rate of the bistable SR system with coherent receiver is derived. Theoretical and numerical results are presented to verify the analysis that the noise can improve the performance of the SR system with non‐coherent receiver. Also, it is shown that the performance of the bistable SR system with coherent receiver is superior to that with non‐coherent receiver, and the background noise is not favourable to signal processing in the coherent receiver.