Scholarlink

The rapid development of blockchain technology has driven the widespread use of smart contracts, but the ensuing security issues have attracted widespread attention. Smart contract vulnerabilities have led to hundreds of millions of dollars of property losses, while existing detection methods are less effective in terms of validity and difficult to effectively explain the causes of vulnerabilities. To this end, this paper proposes a novel Token-Graph model, which extracts function semantic features by pre-training the model and constructs the graph structure by combining the function call relationships. In addition, we trace suspicious functions and their calling relationships to present the risk propagation due to function calls. We compare with 9 vulnerability detection tools on 2,893 contracts. The experimental results show that the Token-Graph model significantly outperforms existing methods in terms of accuracy (86.4%), recall (80.60%), precision (79.02%), and F1-score (79.80%). In addition, we demonstrate the advantages of the model in terms of vulnerability detection interpretability using real cases.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Integrating Pretrained Models with Graph Neural Networks for Smart Contract Interpretability

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Xinxin Hao,
  • Rui Cao,
  • Liming Fang

摘要

The rapid development of blockchain technology has driven the widespread use of smart contracts, but the ensuing security issues have attracted widespread attention. Smart contract vulnerabilities have led to hundreds of millions of dollars of property losses, while existing detection methods are less effective in terms of validity and difficult to effectively explain the causes of vulnerabilities. To this end, this paper proposes a novel Token-Graph model, which extracts function semantic features by pre-training the model and constructs the graph structure by combining the function call relationships. In addition, we trace suspicious functions and their calling relationships to present the risk propagation due to function calls. We compare with 9 vulnerability detection tools on 2,893 contracts. The experimental results show that the Token-Graph model significantly outperforms existing methods in terms of accuracy (86.4%), recall (80.60%), precision (79.02%), and F1-score (79.80%). In addition, we demonstrate the advantages of the model in terms of vulnerability detection interpretability using real cases.