In the context of highly interconnected global markets and the rapid dissemination of multilingual information, traditional risk prediction methods that rely on single numerical sequences or monolingual text are insufficient for achieving early perception of cross-market risks. To address this issue, a cross-market risk early warning framework based on multilingual large language models and multimodal sensing fusion is proposed. The proposed approach is centered on a unified risk semantic space, where cross-lingual semantic alignment is employed to reduce semantic discrepancies across languages. Furthermore, a semantic–volatility coupling attention mechanism is introduced to capture the dynamic relationship between textual semantic evolution and market fluctuations. In addition, cross-market knowledge transfer and low-resource enhancement strategies are incorporated to improve the model’s generalization capability across multilingual and multi-market environments, thereby establishing an intelligent perception and early warning system for complex sensing scenarios. Experimental results demonstrate that the proposed method significantly outperforms multiple baseline models in multilingual cross-market risk prediction tasks. In the main experiment, the model achieves a root mean squared error (RMSE) of $0.1127$, an mean absolute error (MAE) of $0.0846$, and an area under the curve (AUC) of $0.8879$, while the early warning gain is improved to $5.2$ days, which is substantially better than the Transformer model (RMSE $0.1365$, AUC $0.8042$) and the multilingual BERT-based fusion model (AUC $0.8395$). In terms of classification performance, higher accuracy, precision, and recall are consistently achieved, with overall accuracy exceeding $0.88$, and both precision and recall are maintained above $0.85$, indicating strong discriminative capability in risk identification tasks. Cross-lingual generalization experiments further verify the robustness of the proposed framework. When trained solely on the English market, the model achieves AUC values of $0.8624$ and $0.8471$ on the Chinese and European markets, respectively, with RMSE reduced to $0.1185$, significantly outperforming competing methods. Overall, the proposed approach achieves substantial improvements in prediction accuracy, cross-lingual generalization, and early warning performance, providing an effective solution for artificial intelligence-driven sensing and risk early warning.

Anomalous transaction behaviors in cryptocurrency markets exhibit high concealment, substantial diversity, and strong cross-modal coupling, making traditional rule-based or single-feature analytical methods insufficient for reliable detection in real-world environments. To address the research focus, a data-centric multimodal anomaly detection framework integrating generative augmentation, latent distribution modeling, and dual-branch real-time detection is proposed. The method employs a generative adversarial network with feature-consistency constraints to mitigate the scarcity of fraudulent samples, and adopts a multi-domain variational modeling strategy to learn the latent distribution of normal behaviors, enabling stable anomaly scoring. By combining the long-range temporal modeling capability of Transformer architectures with the sensitivity of online clustering to local structural deviations, the system dynamically integrates global and local information through an adaptive risk fusion mechanism, thereby enhancing robustness and real-time detection capability. Experimental results demonstrate that the generative augmentation module yields substantial improvements, increasing the recall from $0.421$ to $0.671$ and the F1-score to $0.692$. In anomaly distribution modeling, the multi-domain VAE achieves an area under the curve (AUC) of $0.854$ and an F1-score of $0.660$, significantly outperforming traditional One-Class SVM and autoencoder baselines. Multimodal fusion experiments further verify the complementarity of the dual-branch detection structure, with the adaptive fusion model achieving an AUC of $0.884$, an F1-score of $0.713$, and reducing the false positive rate to $0.087$. Ablation studies show that the complete model surpasses any individual module in terms of precision, recall, and F1-score, confirming the synergistic benefits of its integrated components. Overall, the proposed framework achieves high accuracy and high recall in data-scarce, structurally complex, and latency-sensitive cryptocurrency scenarios, providing a scalable and efficient solution for deploying data-centric artificial intelligence in financial security applications.

In social sensing environments, misinformation and coordinated manipulation often manifest through implicit semantic signals, complex behavioral dynamics, and highly coupled propagation structures. These factors pose significant challenges to artificial intelligence-driven sensing systems regarding data quality, multimodal fusion, and robustness. To address these issues, this study proposes an artificial intelligence-driven multi-granularity sensing framework. This framework integrates heterogeneous sensing signals from post-level semantic perception, user-level behavioral sensing, and group-level structural sensing into a unified representation space. Hierarchical consistency constraints enable cross-granularity sensing collaboration. This mechanism enhances stability and discriminative capability under complex and noisy data conditions. Methodologically, the framework jointly incorporates semantic sensing via text encoding, temporal sensing via behavioral sequence modeling, and structural sensing via graph neural network-based propagation. This integration effectively mitigates information bias induced by single-perspective sensing and improves the modeling of latent risk patterns. Experimental results on real-world datasets demonstrate that the proposed framework achieves significant improvements across multiple evaluation metrics. Specifically, it achieves a Precision of 0.847, a Recall of 0.812, an F1-score of 0.829, an Accuracy of 0.856, and an Area Under Curve of 0.913. It consistently outperforms traditional machine learning models, as well as mainstream deep learning and graph-based approaches. Furthermore, comparison experiments validate the complementarity among semantic, behavioral, and structural sensing signals. The full model achieves an improvement of more than 3 percentage points in the F1-score compared to single-granularity configurations. An ablation study further demonstrates that each sensing module contributes substantially to performance enhancement, with the semantic sensing and hierarchical consistency constraints playing particularly critical roles. Overall, the proposed method exhibits a strong capability to handle complex heterogeneous sensing data. It improves robustness and enhances cross-level information utilization, providing an effective solution to data-related challenges in artificial intelligence-driven sensing systems.