Graph Neural Networks (GNNs) have demonstrated remarkable utility across diverse applications, and their growing complexity has made Machine Learning as a Service (MLaaS) a viable platform for scalable deployment. However, this accessibility also exposes GNN to serious security threats, most notably model extraction attacks (MEAs), in which adversaries strategically query a deployed model to construct a high-fidelity replica. In this work, we evaluate the vulnerability of GNNs to MEAs and explore their potential for cost-effective model acquisition in non-adversarial research settings. Importantly, adaptive node querying strategies can also serve a critical role in research, particularly when labeling data is expensive or time-consuming. By selectively sampling informative nodes, researchers can train high-performing GNNs with minimal supervision, which is particularly valuable in domains such as biomedicine, where annotations often require expert input. To address this, we propose a node querying strategy tailored to a highly practical yet underexplored scenario, where bulk queries are prohibited, and only a limited set of initial nodes is available. Our approach iteratively refines the node selection mechanism over multiple learning cycles, leveraging historical feedback to improve extraction efficiency. Extensive experiments on benchmark graph datasets demonstrate our superiority over comparable baselines on accuracy, fidelity, and F1 score under strict query-size constraints. These results highlight both the susceptibility of deployed GNNs to extraction attacks and the promise of ethical, efficient GNN acquisition methods to support low-resource research environments. Our implementation is publicly available at [https://github.com/LabRAI/CEGA](https://github.com/LabRAI/CEGA).

Fluid antennas (FA) offer a revolutionary breakthrough in wireless communications by dynamically regulating antenna positions within confined spaces to significantly enhance system capacity and link reliability. In this paper, a FA integrated and reconfigurable intelligent surface empowered receive spatial modulation (FA-RIS-RSM) scheme is proposed. Specifically, due to the unique physical properties of FA, we propose two port selection strategies, namely the random port selection (RPS) and optimal port selection (OPS), to assist the transmission achieving with distinct extents of reliability. Furthermore, we derive closed-form expressions for the average bit error probability (ABEP), via utilizing the Gamma approximation analysis and correlated fading analogism analysis methods, respectively. Simulated and numerical performance results corroborate the correctness of the derivations, as well as demonstrate the superiority and effectiveness of the proposed FA-RIS-RSM in enhancing the wireless transmission reliability.

This article investigates the covert performance of the finite block length device-to-device (D2D) transmission between the multiantenna transceivers assisted by a decode-and-forward (DF) relay node, where the adversary in covert communication, the warden, also employs a multiantenna maximum likelihood detector which observes the covert signals from the source and the relay for joint detection. The relay periodically transmits reference signals to improve the throughput rate over the fading channels while the source and destination estimate the channel coefficients for beamforming. The nonideal beamforming performance with limited reference signals is analyzed, the covert performances measured by the expected relative entropies of the warden’s joint detection are derived, and the optimal power allocation strategy to achieve the highest covert performance under the required throughput rate and outage probabilities is formulated in this article. The theoretical analysis and the numerical results illustrate that the communication side will achieve higher covertness if the relay and the source adopt uncorrelated codes, and the increase in the warden’s antenna number would rapidly improve its detection performance. The numerical results also depict that enhancing the source-to-relay covert transmission brings more improvements for the covertness than the relay-to-destination link, showing the asymmetry between the different links of the DF-relay-assisted covert communication.

With the emergence of the fifth generation (5G) era, the development of the Internet of Things (IoT) network has been accelerated with a new impetus, making it imperative to strive for a more reliable and efficient network environment. To accomplish this, we introduce and investigate a novel proposal for the intelligent reflecting surface (IRS) enabled uplink secure receive spatial modulation (SM), named IRS-USRSM, to resolve the security issues arising from the open wireless transmission environment in the 5G IoT network. In the IRS-USRSM scheme, we assume that the passive eavesdropper is directly connected to the uplink user and occasionally connected to the IRS. To achieve enhanced secrecy with finite alphabet inputs, a joint transmitter perturbation and IRS reflection design for physical layer security is proposed to guarantee secure and reliable transmission of IRS-USRSM. Specifically, two categories of IRS-based random phase compensation strategies, namely, random perturbation compensation and random path synthesize, along with maximum likelihood detection and suboptimal detection are proposed to meet the variant design requirements between achieved performance and system cost. Furthermore, in order to evaluate the performance limits of the IRS-USRSM, the closed-form results of average bit error probabilities and discrete-input continuous-output memoryless channel capacities are derived using the method of moment generating function. Simulation results are presented to verify the correctness of our theoretical analyses, as well as to demonstrate the efficiency and superiority of the proposed IRS-USRSM scheme.

Covert wireless communication intends to prevent hostile surveillance but is threatened by the powerful multi-antenna detection technique. In this paper, we investigate finite blocklength covert communication assisted by a multi-antenna relay station and a multi-antenna destination to fight against hostile detection from a warden also equipped with multiple antennas and interference from an uninformed jammer. In order to achieve optimal covert communication performance, we formulate the optimization problems in the single-user and the frequency division multiple access (FDMA) multi-user scenarios separately. In the single-user scenario, we design a cooperative beamforming strategy for the relay and the destination to maximize their received signal-to-interference-plus-noise (SINR). Then in the multi-user scenario, we utilize the above beamforming strategy and propose a majorization-minimization-based relay’s power allocation algorithm to maximize the total covert throughput rate. The numerical results are provided to depict the effectiveness of the proposed scheme, and we address how the jamming power and the numbers of antennas affect covert communication based on these numerical results and theoretical analysis.

In this paper, we address finite block-length covert wireless communication against an adversary that not only detects the signals but also localizes the source. Because of the probability of failed localization, the adversary’s detection strategy differs greatly from the former works. In the free space propagation model, we discuss the surveillance strategy of an adversary equipped with a uniform linear antenna array and the legitimate users’ resources optimization scheme for achieving covert communication. The theoretical analysis and the numerical results illustrate the properties of the adversary’s surveillance and the achievable covert communication performance, showing that the randomness in the source’s transmission time may also improve the covertness.

To address the security issues in wireless transmission communication systems with finite-alphabet inputs, a secure uplink reception scheme based on receiver spatial modulation is proposed to ensure high security of the wireless transmission system while achieving high spectrum efficiency. The proposed scheme introduces disturbance phase updates at the transmitter end and disturbance compensation at the intelligent reflecting surface (IRS) to ensure both the spectrum efficiency and physical layer security of the wireless transmission system. This enables the legitimate receiver to correctly receive the signal at maximum power while preventing eavesdroppers from accurately intercepting the signal. In this paper, we propose two phase compensation schemes, namely, element-wise random disturbance compensation (ERDC) and group-wise random disturbance compensation. Furthermore, two eavesdropping scenarios, referred to as ideal eavesdropping and jamming eavesdropping, are thoroughly investigated and considered. We introduce the maximum likelihood detection to reliably detecte the indices of the designed receive antenna and the based-band modulated signal, and the closed-form expressions of error performance with ERDC scheme are deduced. Finally, in the simulated and numercial results, the performance analysis verifies error performance discrepancy based security performance evaluation of the proposed scheme, demonstrating its effectiveness and superiority.

Abstract Protein ligand docking is an indispensable tool for computational prediction of protein functions and screening drug candidates. Despite significant progress over the past two decades, it is still a challenging problem, characterized by the still limited understanding of the energetics between proteins and ligands, and the vast conformational space that has to be searched to find a satisfactory solution. In this project, we developed a novel reinforcement learning (RL) approach, the asynchronous advantage actor-critic model (A3C), to address the protein ligand docking problem. The overall framework consists of two models. During the search process, the agent takes an action selected by the actor model based on the current location. The critic model then evaluates this action and predict the distance between the current location and true binding site. Experimental results showed that in both single- and multi-atom cases, our model improves binding site prediction substantially compared to a naïve model. For the single-atom ligand, copper ion (Cu2+), the model predicted binding sites have a median root-mean-square-deviation (RMSD) of 2.39 Å to the true binding sites when starting from random starting locations. For the multi-atom ligand, sulfate ion (SO42−), the predicted binding sites have a median RMSD of 3.82 Å to the true binding sites. The ligand-specific models built in this study can be used in solvent mapping studies and the RL framework can be readily scaled up to larger and more diverse sets of ligands.

In this paper, we define the metric "detectable area" to measure the covertness of covert communication in a practical way. Detectable area is the area where interceptor can achieve acceptance probability of detection with desired probability of false alarm. By computing the detectable areas of single and multi-antenna interceptors in line-of-sight (LOS) channel scenario, we find that single jammer may do more harm than good on covert communication when interceptor is equipped with multi-antenna detector. This impact should be considered while designing covert communication system in the presence of jammer.