Detection of smart contract Ponzi schemes based on graph convolutional neural networks

ZHANG Yanmei; GUO Siying; JIA Hengyue; JIANG Rong

doi:10.11959/j.issn.1000-436x.2025156

您当前的位置：

首页 >

文章列表页 >

Detection of smart contract Ponzi schemes based on graph convolutional neural networks

Correspondences | 更新时间：2025-10-27

- Detection of smart contract Ponzi schemes based on graph convolutional neural networks
- Journal on Communications Vol. 46, Issue 9, Pages: 292-306(2025)
- 作者机构：
  
  1.中央财经大学信息学院，北京 100081
  2.四川农商联合银行信息科技部，四川成都 610041
  3.云南财经大学云南省服务计算重点实验室，云南昆明 650221
- 作者简介：
- 基金信息：
  
  The National Key Research and Development Program of China(2024YFC3308100);The National Natural Science Foundation of China(62372493)
- DOI：10.11959/j.issn.1000-436x.2025156
  CLC： TP393
- Received：12 May 2025，
  
  Revised：2025-09-06，
  
  Accepted：08 September 2025，
  
  Published：25 September 2025
- 稿件说明：
移动端阅览
张艳梅,郭思颖,贾恒越等.以太坊庞氏骗局智能合约的早期检测方法研究[J].通信学报,2025,46(09):292-306.

ZHANG Yanmei,GUO Siying,JIA Hengyue,et al.Detection of smart contract Ponzi schemes based on graph convolutional neural networks[J].Journal on Communications,2025,46(09):292-306.
张艳梅,郭思颖,贾恒越等.以太坊庞氏骗局智能合约的早期检测方法研究[J].通信学报,2025,46(09):292-306. DOI： 10.11959/j.issn.1000-436x.2025156.

ZHANG Yanmei,GUO Siying,JIA Hengyue,et al.Detection of smart contract Ponzi schemes based on graph convolutional neural networks[J].Journal on Communications,2025,46(09):292-306. DOI： 10.11959/j.issn.1000-436x.2025156.

摘要

以太坊是区块链的典型应用代表，它允许开发者创建和执行智能合约。以太坊技术的迅猛发展在推动智能合约普及的同时，也引发链上安全风险剧增，其中算法驱动的智能庞氏骗局给区块链应用带来了新的安全挑战。为了实现对智能合约庞氏骗局的早期检测，提出了一种基于图卷积网络（GCN）的检测方法PonziGCN。该方法融合了智能合约的语义特征和控制流图特征，通过提取字节码相似度、操作码频率等语义特征，以及控制流图的基本特征和结构特征，构建了多特征融合的检测框架。实验结果表明，所提方法在精确率、召回率、F值和AUC值等关键性能指标上均表现优异，精确率达到0.982，召回率为0.987，F值为0.978，AUC值为0.983，显著优于现有的算法。特征重要性分析表明，图结构特征和代码中与交易功能相关的操作码频率特征在模型中具有最高的重要性。

Abstract

Ethereum is an application of blockchain that allows developers to create and execute smart contracts. With the rapid development of Ethereum technology

the widespread application of smart contracts has introduced new security challenges

particularly the proliferation of fraudulent contracts such as Ponzi schemes. To achieve early detection of Ponzi schemes in smart contracts

a detection model named PonziGCN based on graph convolutional network (GCN) was proposed. The model integrated semantic features and control flow graph features of smart contracts. By extracting semantic features such as bytecode similarity and opcode frequency

as well as basic and structural features of control flow graphs

a multi-feature fusion detection framework was constructed. Experimental results demonstrate that the PonziGCN model performed excellently in key performance metrics

achieving an accuracy of 0.982

a recall of 0.987

an F-score of 0.978

and an AUC value of 0.983

significantly outperforming existing advanced algorithms. Feature importance analysis indicates that graph structural features and opcode frequency features related to transaction functions in the code hold the highest importance in the model.

关键词

Keywords

references

SZABO N . Smart contracts: building blocks for digital markets [J ] . EXTROPY: The Journal of Transhumanist Thought , 1996 , 18 ( 2 ): 28 .

BARTOLETTI M , CARTA S , CIMOLI T , et al . Dissecting Ponzi schemes on ethereum: identification, analysis, and impact [J ] . Future Generation Computer Systems , 2020 , 102 : 259 - 277 .

ZHANG Y M , KANG S Q , DAI W , et al . Code will speak: early detection of ponzi smart contracts on ethereum [C ] // Proceedings of the 2021 IEEE International Conference on Services Computing (SCC) . Pisca-taway : IEEE Press , 2021 : 301 - 308 .

WU J J , LIU J L , CHEN J Z , et al . ContraPonzi: smart ponzi scheme detection for ethereum via contrastive learning [C ] // Proceedings of the 2023 4th Asia Service Sciences and Software Engineering Conference . New York : ACM Press , 2023 : 155 - 162 .

LIANG R C , CHEN J , HE K , et al . Ponziguard: detecting ponzi schemes on ethereum with contract runtime behavior graph (CRBG) [C ] // Proceedings of the 2024 IEEE/ACM 46th International Conference on Software Engineering (ICSE) . Piscataway : IEEE Press , 2024 : 766 - 777 .

BARTOLETTI M , PES B , SERUSI S . Data mining for detecting Bitcoin ponzi schemes [C ] // Proceedings of the 2018 Crypto Valley Conference on Blockchain Technology (CVCBT) . Piscataway : IEEE Press , 2018 : 75 - 84 .

JIN C X , JIN J , ZHOU J J , et al . Heterogeneous feature augmentation for ponzi detection in ethereum [J ] . IEEE Transactions on Circuits and Systems II: Express Briefs , 2022 , 69 ( 9 ): 3919 - 3923 .

ZHENG Z B , CHEN W L , ZHONG Z J , et al . Securing the ethereum from smart ponzi schemes: identification using static features [J ] . ACM Transactions on Software Engineering and Methodology , 2023 , 32 ( 5 ): 1 - 28 .

CHEN W L , ZHENG Z B , NGAI E C H , et al . Exploiting blockchain data to detect smart ponzi schemes on ethereum [J ] . IEEE Access , 2019 , 7 : 37575 - 37586 .

LINNHOFF-POPIEN C , SCHNEIDER R , ZADDACH M . Digital marketplaces unleashed [M ] . Berlin : Springer , 2018 .

QIAN P , LIU Z G , HE Q M , et al . Towards automated reentrancy detection for smart contracts based on sequential models [J ] . IEEE Access , 2020 , 8 : 19685 - 19695 .

LIU Z G , QIAN P , WANG X Y , et al . Combining graph neural networks with expert knowledge for smart contract vulnerability detection [J ] . IEEE Transactions on Knowledge and Data Engineering , 2023 , 35 ( 2 ): 1296 - 1310 .

ZHUANG Y , LIU Z G , QIAN P , et al . Smart contract vulnerability detection using graph neural network [C ] // Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence . Pisca-taway : IEEE Press , 2020 : 3283 - 3290 .

CHEN C , SU J Z , CHEN J C , et al . When ChatGPT meets smart contract vulnerability detection: how far are we? [J ] . ACM Transactions on Software Engineering and Methodology , 2025 , 34 ( 4 ): 1 - 30 .

VASEK M , MOORE T . Analyzing the Bitcoin ponzi scheme ecosystem [C ] // Financial Cryptography and Data Security . Berlin : Springer , 2019 : 101 - 112 .

TORRES C F , STEICHEN M , STATE R . The art of the scam: demystifying honeypots in Ethereum smart contracts [C ] // Proceedings of the 28th USENIX Conference on Security Symposium . Berkeley : USENIX Association , 2019 : 1591 - 1607 .

CHEN W L , GUO X F , CHEN Z G , et al . Honeypot contract risk warning on ethereum smart contracts [C ] // Proceedings of the 2020 IEEE International Conference on Joint Cloud Computing . Piscataway : IEEE Press , 2020 : 1 - 8 .

ZHANG Y M , YU W Q , LI Z Y , et al . Detecting ethereum ponzi schemes based on improved LightGBM algorithm [J ] . IEEE Transactions on Computational Social Systems , 2022 , 9 ( 2 ): 624 - 637 .

ZHOU Y , KUMAR D , BAKSHI S , et al . Erays: reverse engineering ethereum's opaque smart contracts [C ] // Proceedings of the 27th USENIX Conference on Security Symposium . Berkeley : USENIX Association , 2018 : 1371 - 1385 .

CHEN T , LI Z H , LUO X P , et al . Poster: SigRec - automatic recovery of function signatures in smart contracts [C ] // Proceedings of the 2023 IEEE 43rd International Conference on Distributed Computing Systems (ICDCS) . Piscataway : IEEE Press , 2023 : 1065 - 1066 .

ZHAO K S , LI Z H , LI J F , et al . DeepInfer: deep type inference from smart contract bytecode [C ] // Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering . New York : ACM Press , 2023 : 745 - 757 .

ALLEN F E . Control flow analysis [J ] . ACM SIGPLAN Notices , 1970 , 5 ( 7 ): 1 - 19 .

KIPF T N , WELLING M . Semi-supervised classification with graph convolutional networks [J ] . arXiv Preprint , arXiv: 1609.02907 , 2016 .

LOU Y C , ZHANG Y M , CHEN S P . Ponzi contracts detection based on improved convolutional neural network [C ] // Proceedings of the 2020 IEEE International Conference on Services Computing (SCC) . Piscataway : IEEE Press , 2020 : 353 - 360 .

CUTLER A , CUTLER D R , STEVENS J R . Random forests [J ] . Machine Learning , 2004 , 45 ( 1 ): 157 - 176

CHEN T Q , GUESTRIN C . XGBoost: a scalable tree boosting system [C ] // Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . New York : ACM Press , 2016 : 785 - 794 .

PINKUS A . Approximation theory of the MLP model in neural networks [J ] . Acta Numerica , 1999 , 8 : 143 - 195 .

VELIČKOVIĆ P , CUCURULL G , CASANOVA A , et al . Graph attention networks [J ] . arXiv Preprint , arXiv: 1710.10903 , 2017 .

Views

589

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Honeypot contract detection of blockchain based on deep learning

A Covert Communication Method Based on Ethereum Bytecode

Smart contract vulnerability detection method based on Bi-modal cross-attention mechanism

Byzantine fault-tolerant distributed access control mechanism for the Internet of things

Lightweight and secure search scheme for medical data sharing

Related Author

Ben WANG

Dengyue WANG

Qi WANG

Hongxia ZHANG

Huang Min

Huang Dongyan

CHEN Jinfu

HU Xinyi

Related Institution

Qingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum

Ministry of Education Key Lab. of Cognitive Radio and Information Processing

School of Information and Communication Technology, Guilin University of Electronic Technology

Jiangsu Key Laboratory of Security Technology for Industrial Cyberspace, Jiangsu University

School of Computer Science and Communication Engineering, Jiangsu University

AI问答

⁰