Smart Contract Vulnerability Detection using Graph Neural Network

TLDR

Smart contract security has attracted attention due to large financial losses from vulnerabilities, and current detection methods that rely on fixed expert rules suffer from low accuracy. This work investigates the use of graph neural networks (GNNs) to detect vulnerabilities in smart contracts. The authors build a contract graph capturing syntactic and semantic structures, normalize it via an elimination phase, and then apply a degree‑free graph convolutional network (DR‑GCN) together with a temporal message propagation network (TMP) to learn from the graphs. Experiments demonstrate that the proposed approach markedly outperforms existing state‑of‑the‑art methods in detecting three types of vulnerabilities.

Abstract

The security problems of smart contracts have drawn extensive attention due to the enormous financial losses caused by vulnerabilities. Existing methods on smart contract vulnerability detection heavily rely on fixed expert rules, leading to low detection accuracy. In this paper, we explore using graph neural networks (GNNs) for smart contract vulnerability detection. Particularly, we construct a contract graph to represent both syntactic and semantic structures of a smart contract function. To highlight the major nodes, we design an elimination phase to normalize the graph. Then, we propose a degree-free graph convolutional neural network (DR-GCN) and a novel temporal message propagation network (TMP) to learn from the normalized graphs for vulnerability detection. Extensive experiments show that our proposed approach significantly outperforms state-of-the-art methods in detecting three different types of vulnerabilities.