LIGHTPONZI: Efficient Multimodal Detection of Ponzi Schemes in Ethereum Smart Contracts

Abstract

The rapid growth of decentralized finance on Ethereum has facilitated the rise of fraudulent Ponzi schemes, which exploit blockchain immutability and pseudonymity to deceive investors. Existing detection methods, often fail to generalize to evolving attack strategies, while current multimodal approaches suffer from high computational overhead. To address these challenges, we propose LightPonzi, a lightweight multimodal framework that integrates transaction graphs, abstract syntax trees, and textual semantics of smart contracts. By leveraging GraphSAGE and DistilBERT, LightPonzi efficiently encodes structural, behavioral, and semantic features, which are fused for accurate classification. Extensive experiments on a curated dataset of Ethereum contracts demonstrate that LightPonzi achieves a balanced F1 score of 0.911 while processing each contract in 80.11 ms on average, outperforming state-of-the-art baselines in both effectiveness and efficiency. Our framework provides a practical solution for real-time Ponzi scheme detection.