基于双模态交叉注意力机制的智能合约漏洞检测方法

陈锦富; 胡心怡; 蔡赛华; 闵玺润

doi:10.11959/j.issn.1000-436x.2025107

您当前的位置：

首页 >

文章列表页 >

基于双模态交叉注意力机制的智能合约漏洞检测方法

学术论文 | 更新时间：2025-07-04

- 基于双模态交叉注意力机制的智能合约漏洞检测方法
- Smart contract vulnerability detection method based on Bi-modal cross-attention mechanism
- 通信学报 2025年46卷第6期页码：218-232
- 作者机构：
  
  1.江苏大学计算机科学与通信工程学院，江苏镇江 212013
  2.江苏省工业网络安全技术重点实验室，江苏镇江 212013
- 作者简介：
  
  [ "陈锦富（1978- ），男，江西赣州人，博士，江苏大学教授、博士生导师，主要研究方向为软件测试、软件安全和可信软件。" ]
  [ "胡心怡（2000- ），男，江苏常州人，江苏大学硕士生，主要研究方向为区块链漏洞检测、软件安全测试。" ]
  [ "蔡赛华（1990- ），男，江苏南通人，博士，江苏大学副教授、硕士生导师，主要研究方向为恶意流量检测、异常数据检测、软件安全测试。" ]
  [ "闵玺润（2001- ），男，江苏无锡人，江苏大学硕士生，主要研究方向为智能合约漏洞检测、软件安全。" ]
- 基金信息：
  
  国家重点研发计划基金资助项目;The National Key Research and Development Program of China(2020YFB1005501);国家自然科学基金资助项目(62172194;62202206;U1836116);江苏省前沿引领技术基础研究专项基金资助项目;The Leading-edge Technology Program of Jiangsu Natural Science Foundation(BK20202001);江苏省青蓝工程基金资助项目
- DOI：10.11959/j.issn.1000-436x.2025107
  中图分类号： TP311
- 收稿日期：2025-03-10，
  
  修回日期：2025-06-03，
  
  纸质出版日期：2025-06-25
- 稿件说明：
移动端阅览
陈锦富,胡心怡,蔡赛华等.基于双模态交叉注意力机制的智能合约漏洞检测方法[J].通信学报,2025,46(06):218-232.

CHEN Jinfu,HU Xinyi,CAI Saihua,et al.Smart contract vulnerability detection method based on Bi-modal cross-attention mechanism[J].Journal on Communications,2025,46(06):218-232.
陈锦富,胡心怡,蔡赛华等.基于双模态交叉注意力机制的智能合约漏洞检测方法[J].通信学报,2025,46(06):218-232. DOI： 10.11959/j.issn.1000-436x.2025107.

CHEN Jinfu,HU Xinyi,CAI Saihua,et al.Smart contract vulnerability detection method based on Bi-modal cross-attention mechanism[J].Journal on Communications,2025,46(06):218-232. DOI： 10.11959/j.issn.1000-436x.2025107.

摘要

针对智能合约漏洞检测中现有深度学习方法依赖单一模态进行特征提取、对上下文信息捕获不足导致检测准确率较低的问题，提出了一种基于双模态交叉注意力机制的智能合约漏洞检测方法，设计了特定的注意力机制，同时分析合约的源代码和字节码，实现源代码中的高级语义特征与字节码中的底层执行流程双向映射和互补增强，丰富特征表示。引入的残差连接有效地保持和传递原始特征信息，缓解深层网络训练中的梯度消失问题。在公开数据集上进行广泛测试，实验结果表明，所提方法相较基线提高了检测准确率2%以上；消融实验结果显示，跨模态特征融合和注意力机制的设计相互协同，显著提升检测性能。

Abstract

To address the problem that existing deep learning methods for smart contract vulnerability detection rely on single-modal feature extraction and insufficient contextual information capture

leading to relatively low detection accuracy

a smart contract vulnerability detection method based on the Bi-modal cross-attention mechanism was proposed. A specific attention mechanism was designed that simultaneously analyzed both contract source code and bytecode

achieving bidirectional mapping and complementary enhancement between high-level semantic features in source code and low-level execution flows in bytecode

thereby enriching feature representation. Residual connections were introduced to effectively preserve and transmit original feature information

mitigating the vanishing gradient problem in deep network training. Extensive testing on public datasets demonstrates that the proposed method improves detection accuracy by more than 2% compared to baselines. Ablation experiments confirm that cross-modal feature fusion and the design of the attention mechanism work in synergy with each other

significantly improving the detection performance.

关键词

Keywords

references

CHEN S J , MI H N , PING J , et al . A blockchain consensus mechanism that uses proof of solution to optimize energy dispatch and trading [J ] . Nature Energy , 2022 , 7 : 495 - 502 .

GAI K K , ZHANG Y , QIU M K , et al . Blockchain-enabled service optimizations in supply chain digital twin [J ] . IEEE Transactions on Services Computing , 2023 , 16 ( 3 ): 1673 - 1685 .

GAI K K , WU Y L , ZHU L H , et al . Privacy-preserving energy trading using consortium blockchain in smart grid [J ] . IEEE Transactions on Industrial Informatics , 2019 , 15 ( 6 ): 3548 - 3558 .

ZICHICHI M , CONTU M , FERRETTI S , et al . LikeStarter: a smart-contract based social DAO for crowdfunding [C ] // Proceedings of the IEEE INFOCOM 2019 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) . Piscataway : IEEE Press , 2019 : 313 - 318 .

TIKHOMIROV S , VOSKRESENSKAYA E , IVANITSKIY I , et al . SmartCheck: static analysis of ethereum smart contracts [C ] // Proceedings of the 2018 IEEE/ACM 1st International Workshop on Emerging Trends in Software Engineering for Blockchain (WETSEB) . Piscataway : IEEE Press , 2018 : 9 - 16 .

LUU L , CHU D H , OLICKEL H , et al . Making smart contracts smarter [C ] // Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security . New York : ACM Press , 2016 : 254 - 269 .

TSANKOV P , DAN A , DRACHSLER-COHEN D , et al . Securify: practical security analysis of smart contracts [C ] // Proceedings of the 2018 ACM SIGSAC Conference on Computer and Communications Security . New York : ACM Press , 2018 : 67 - 82 .

FEIST J , GRIECO G , GROCE A . Slither: a static analysis framework for smart contracts [C ] // Proceedings of the 2019 IEEE/ACM 2nd International Workshop on Emerging Trends in Software Engineering for Blockchain (WETSEB) . Piscataway : IEEE Press , 2019 : 8 - 15 .

JIANG B , LIU Y , CHAN W K . ContractFuzzer: fuzzing smart contracts for vulnerability detection [C ] // Proceedings of the 2018 33rd IEEE/ACM International Conference on Automated Software Engineering (ASE) . Piscataway : IEEE Press , 2018 : 259 - 269 .

SHARMA N , SHARMA S . A survey of Mythril, a smart contract security analysis tool for EVM bytecode [J ] . Indian Journal of Natural Products and Resources , 2022 , 13 ( 75 ): 39 - 41 .

钱鹏 , 刘振广 , 何钦铭 , 等 . 智能合约安全漏洞检测技术研究综述 [J ] . 软件学报 , 2022 , 33 ( 8 ): 3059 - 3085 .

QIAN P , LIU Z G , HE Q M , et al . Smart contract vulnerability detection technique: a survey [J ] . Journal of Software , 2022 , 33 ( 8 ): 3059 - 3085 .

QIAN P , LIU Z G , YIN Y F , et al . Cross-modality mutual learning for enhancing smart contract vulnerability detection on bytecode [C ] // Proceedings of the ACM Web Conference 2023 . New York : ACM Press , 2023 : 2220 - 2229 .

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 .

LUO F , LUO R J , CHEN T , et al . SCVHUNTER: smart contract vulnerability detection based on heterogeneous graph attention network [C ] // Proceedings of the 2024 IEEE/ACM 46th International Conference on Software Engineering (ICSE) . Piscataway : IEEE Press , 2024 : 2098 - 2110 .

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

WU H J , ZHANG Z , WANG S W , et al . Peculiar: smart contract vulnerability detection based on crucial data flow graph and pre-training techniques [C ] // Proceedings of the 2021 IEEE 32nd International Symposium on Software Reliability Engineering (ISSRE) . Piscataway : IEEE Press , 2021 : 378 - 389 .

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 .

VIDAL F R , IVAKI N , LARANJEIRO N . Vulnerability detection techniques for smart contracts: a systematic literature review [J ] . Journal of Systems and Software , 2024 , 217 : 112160 .

KHAN Z A , NAMIN A S . A survey of vulnerability detection techniques by smart contract tools [J ] . IEEE Access , 2024 , 12 : 70870 - 70910 .

CHEN J C , CHEN C , HU J , et al . Identifying smart contract security issues in code snippets from stack overflow [C ] // Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis . New York : ACM , 2024 : 1198 - 1210 .

CHEN H Y , ZHAO X F , WANG Y C , et al . SafeCheck: detecting smart contract vulnerabilities based on static program analysis methods [J ] . Security and Privacy , 2024 , 7 ( 5 ): e393 .

CAI J , LI B , ZHANG T , et al . Fine-grained smart contract vulnerability detection by heterogeneous code feature learning and automated dataset construction [J ] . Journal of Systems and Software , 2024 , 209 : 111919 .

YANG H W , GU X G , CHEN X , et al . CrossFuzz: cross-contract fuzzing for smart contract vulnerability detection [J ] . Science of Computer Programming , 2024 , 234 : 103076 .

ZHANG L J , LI Y , GUO R , et al . A novel smart contract reentrancy vulnerability detection model based on BiGAS [J ] . Journal of Signal Processing Systems , 2024 , 96 ( 3 ): 215 - 237 .

COLIN L S H , MOHAN P M , PAN J , et al . An integrated smart contract vulnerability detection tool using multi-layer perceptron on real-time solidity smart contracts [J ] . IEEE Access , 2024 , 12 : 23549 - 23567 .

ALLAMANIS M , BROCKSCHMIDT M , KHADEMI M . Learning to represent programs with graphs [C ] // International Conference on Learning Representations . Vancouver : ICLR , 2018 : 1 - 17 .

VELIČKOVIĆ P , CUCURULL G , CASANOVA A , et al . Graph attention networks [C ] // International Conference on Learning Representations . Vancouver : ICLR , 2018 : 1 - 12 .

VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [J ] . Advances in Neural Information Processing Systems , 2017 , 30 : 5998 - 6008 .

GU X , CHEN G , WANG Y F , et al . Text with knowledge graph augmented transformer for video captioning [C ] // Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE Press , 2023 : 18941 - 18951 .

DURIEUX T , FERREIRA J F , ABREU R , et al . Empirical review of automated analysis tools on 47,587 Ethereum smart contracts [C ] // Proceedings of the ACM/IEEE 42nd International Conference on Software Engineering . Piscataway : IEEE Press , 2020 : 530 - 541 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于预训练与新型时序图神经网络的智能合约漏洞检测方法

基于深度学习的区块链蜜罐陷阱合约检测

基于并行流量图和图神经网络的加密流量分类方法

基于深度学习的通感一体化系统综述

基于SFNet的大规模MIMO系统的CSI反馈算法