Smart Contract Vulnerability Detection: From Pure Neural Network to Interpretable Graph Feature and Expert Pattern Fusion

TLDR

Smart contracts hold billions of dollars in digital coins, yet their security has attracted attention, and conventional rule‑based detection suffers from low accuracy and poor scalability, while recent deep‑learning methods improve performance but fail to incorporate expert knowledge. The study investigates an explainable fusion of deep learning with expert patterns for smart contract vulnerability detection. We automatically extract expert patterns from source code, transform the code into a semantic graph to obtain deep graph features, and fuse these global graph features with local expert patterns using interpretable weights, evaluating the approach on Ethereum and VNT Chain contracts. The resulting system significantly outperforms state‑of‑the‑art methods, and its code is publicly released.

Abstract

Smart contracts hold digital coins worth billions of dollars, their security issues have drawn extensive attention in the past years. Towards smart contract vulnerability detection, conventional methods heavily rely on fixed expert rules, leading to low accuracy and poor scalability. Recent deep learning approaches alleviate this issue but fail to encode useful expert knowledge. In this paper, we explore combining deep learning with expert patterns in an explainable fashion. Specifically, we develop automatic tools to extract expert patterns from the source code. We then cast the code into a semantic graph to extract deep graph features. Thereafter, the global graph feature and local expert patterns are fused to cooperate and approach the final prediction, while yielding their interpretable weights. Experiments are conducted on all available smart contracts with source code in two platforms, Ethereum and VNT Chain. Empirically, our system significantly outperforms state-of-the-art methods. Our code is released.