PSPL: A Ponzi scheme smart contracts detection approach via compressed sensing oversampling-based peephole LSTM

Abstract

Decentralized Finance (DeFi) utilizes the key principles of blockchain to improve the traditional finance system with greater freedom in trade. However, due to the absence of access restrictions in the implementation of decentralized finance protocols, effective regulatory measures are crucial to ensuring the healthy development of DeFi ecosystems. As a prominent DeFi platform, Ethereum has witnessed an increase in fraudulent activities, with the Ponzi schemes causing significant user losses. With the growing sophistication of Ponzi scheme fraud methods, existing detection techniques fail to effectively identify Ponzi schemes timely. To mitigate the risk of investor deception, we propose PSPL, a compressed sensing oversampling-based Peephole LSTM approach for detecting Ethereum Ponzi schemes. First, we identify Ethereum representative Ponzi schemes’ features by analyzing smart contracts’ codes and user accounts’ temporal transaction information based on the popular XBlock dataset. Second, to address the class imbalance and few-shot learning challenges, we leverage the compressed sensing approach to oversample the Ponzi Scheme samples. Third, peephole LSTM is employed to effectively capture long sequence variations in the fraud features of Ponzi schemes, accurately identifying hidden Ponzi schemes during the transaction process in case fraudulent features are exposed. Finally, experimental results demonstrate the effectiveness and efficiency of PSPL.