Dynamic Feature Fusion: Combining Global Graph Structures and Local Semantics for Blockchain Phishing Detection

The advent of blockchain technology has facilitated the widespread adoption of smart contracts in the financial sector. However, current phishing detection methodologies exhibit limitations in capturing both global structural patterns within transaction networks and local semantic relationships embedded in transaction data. Most existing models focus on either structural information or semantic features individually, leading to suboptimal performance in detecting complex phishing patterns. In this paper, we propose a dynamic feature fusion model that combines graph-based representation learning and semantic feature extraction for blockchain phishing detection. Specifically, we construct global graph representations to model account relationships and extract local contextual features from transaction data. A dynamic multimodal fusion mechanism is introduced to adaptively integrate these features, enabling the model to capture both structural and semantic phishing patterns effectively. We further develop a comprehensive data processing pipeline, including graph construction, temporal feature enhancement, and text preprocessing. Experimental results on large-scale real-world blockchain datasets demonstrate that our method outperforms existing benchmarks across accuracy, F1 score, and recall metrics. This work highlights the importance of integrating structural relationships and semantic similarities for robust phishing detection and offers a scalable solution for securing blockchain systems. Our code is available at https://github.com/dcszhang/DynamicFeature.