Spoofing detection in financial trading is crucial, especially for identifying complex behaviors such as conspiracy spoofing. Traditional machine-learning approaches primarily focus on isolated node features, often overlooking the broader context of interconnected nodes. Graph-based techniques, particularly Graph Neural Networks (GNNs), have advanced the field by leveraging relational information effectively. However, in real-world spoofing detection datasets, trading behaviors exhibit dynamic, irregular patterns. Existing spoofing detection methods, though effective in some scenarios, struggle to capture the complexity of dynamic and diverse, evolving inter-node relationships. To address these challenges, we propose a novel framework called the Generative Dynamic Graph Model (GDGM), which models dynamic trading behaviors and the relationships among nodes to learn representations for conspiracy spoofing detection. Specifically, our approach incorporates the generative dynamic latent space to capture the temporal patterns and evolving market conditions. Raw trading data is first converted into time-stamped sequences. Then we model trading behaviors using the neural ordinary differential equations and gated recurrent units, to generate the representation incorporating temporal dynamics of spoofing patterns. Furthermore, pseudo-label generation and heterogeneous aggregation techniques are employed to gather relevant information and enhance the detection performance for conspiratorial spoofing behaviors. Experiments conducted on spoofing detection datasets demonstrate that our approach outperforms state-of-the-art models in detection accuracy. Additionally, our spoofing detection system has been successfully deployed in one of the largest global trading markets, further validating the practical applicability and performance of the proposed method.

In this article, a dual-function intelligent reflecting surface (IRS) assisted cognitive radio (CR) nonorthogonal multiple access (NOMA) networks for secure transmission is studied. Considering the scenario of both internal and multiple external Eves in the system, our goal is to maximize the sum achievable secrecy rate through jointly optimizing the transmit beamforming of cognitive base station (CBS), the mode selection of each IRS element and the phase vector of IRS, while both the passive dual-function IRS and active dual-function IRS are investigated. For passive dual-function IRS setup, we decouple the proposed nonconvex optimization problem into two subproblems, the transmit beamforming subproblem and the phase vector subproblem. For transmit beamforming subproblem, we first use arithmetic geometric mean (AGM) inequality and linear matrix inequality (LMI) to deal with the nonconvex fraction form in the objective function and in constraints. Then, successive convex approximation (SCA) is applied to iteratively solve it. For the phase vector subproblem, we utilize the penalty function to handle the rank one constraint and the binary constraint. By alternately optimizing these two subproblems, we obtain a local optimal solution. Then, we extend the proposed algorithm to the secure transmission scheme with active dual-function IRS. The simulation results demonstrate that the proposed scheme with the help of a dual-function IRS effectively enhances the security of the CR-NOMA network compared to other benchmark schemes. Moreover, when the maximum transmitting power$P_{\max }\ge 15$dBm, the proposed active IRS scheme is superior to the proposed passive IRS scheme.