SpaTeD: Sparsity-Aware Tensor Decomposition-Based Representation Learning Framework for Phishing Scams Detection

Abstract

In recent years, the consequences of phishing scams on Ethereum have adversely affected the stability of the cryptocurrency environment. Numerous incidents have been reported that have resulted in a substantial loss of cryptocurrency. The existing literature in this area primarily leverages traditional feature engineering or network representation learning to recover crucial information from transaction records to identify suspected users. However, these methods mainly rely on handcrafted feature engineering or conventional node representation learning from a static network while ignoring the network dynamism and inherent temporal sparsity in the user behavior that results in underperformance after an extended period. This article proposes a novel sparsity-aware tensor decomposition-based architecture:SpaTeD, which retrieves efficient user representation utilizing the evolving transaction and structural information and subsequently mitigates the temporal sparsity problem. Our model is evaluated on a real-world Ethereum phishing scam dataset and reports a significant performance improvement over the baselines (96%recalland 96%F1-score). We have conducted an extensive set of experiments to verify the temporal robustness of the model. Additionally, we have provided the ablation study to demonstrate the contribution of each component of the framework.