EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

Smart Contract Vulnerability Detection Based on Deep Learning and Multimodal Decision Fusion

Weichu Deng iD, Huanchun Wei, Teng Huang, Cong Cao, Yun Peng, Xuan Hu

Sensors · 2023-08-18 · 23 (16) · 7246

DOI: 10.3390/s23167246 ↗

At a glance

Journal article in Sensors, published online on 2023-08-18. Written by Weichu Deng and 5 co-authors. Institution: Institute of Artificial Intelligence and Blockchain, Guangzhou University, Guangzhou 510006, China. Cited 64 times so far (Crossref); 70 references. The full text is freely available (open access, CC BY 4.0). Funded by: National Natural Science Foundation of China, NSF of Guangdong Province, the Key Laboratory, Ministry of Industry and Information Technology, China.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

With the rapid development and widespread application of blockchain technology in recent years, smart contracts running on blockchains often face security vulnerability problems, resulting in significant economic losses. Unlike traditional programs, smart contracts cannot be modified once deployed, and vulnerabilities cannot be remedied. Therefore, the vulnerability detection of smart contracts has become a research focus. Most existing vulnerability detection methods are based on rules defined by experts, which are inefficient and have poor scalability. Although there have been studies using machine learning methods to extract contract features for vulnerability detection, the features considered are singular, and it is impossible to fully utilize smart contract information. In order to overcome the limitations of existing methods, this paper proposes a smart contract vulnerability detection method based on deep learning and multimodal decision fusion. This method also considers the code semantics and control structure information of smart contracts. It integrates the source code, operation code, and control-flow modes through the multimodal decision fusion method. The deep learning method extracts five features used to represent contracts and achieves high accuracy and recall rates. The experimental results show that the detection accuracy of our method for arithmetic vulnerability, re-entrant vulnerability, transaction order dependence, and Ethernet locking vulnerability can reach 91.6%, 90.9%, 94.8%, and 89.5%, respectively, and the detected AUC values can reach 0.834, 0.852, 0.886, and 0.825, respectively. This shows that our method has a good vulnerability detection effect. Furthermore, ablation experiments show that the multimodal decision fusion method contributes significantly to the fusion of different modalities.

Subjects

Author keywords

deep learningmultimodal fusionsmart contractvulnerability detection

Authors and institutions

  • Institute of Artificial Intelligence and Blockchain, Guangzhou University, Guangzhou 510006, China.
  • School of Beidou, Guangxi University of Information Engineering, Nanning 530299, China.
  • Information Security Research Center, CEPREI Laboratory, Guangzhou 510610, China.
  • Key Laboratory of Ministry of Industry and Information Technology, Guangzhou 510610, China.

ORCID profiles: Weichu Deng

Funding

  • National Natural Science Foundation of China
  • NSF of Guangdong Province
  • the Key Laboratory, Ministry of Industry and Information Technology, China

Cite

APA

Deng, W., Wei, H., Huang, T., Cao, C., Peng, Y., & Hu, X. (2023). Smart Contract Vulnerability Detection Based on Deep Learning and Multimodal Decision Fusion. Sensors, 23(16), 7246. https://doi.org/10.3390/s23167246

Vancouver

Deng W, Wei H, Huang T, Cao C, Peng Y, Hu X. Smart Contract Vulnerability Detection Based on Deep Learning and Multimodal Decision Fusion. Sensors. 2023;23(16):7246. doi:10.3390/s23167246

BibTeX
@article{Deng2023,
  author = {Deng, Weichu and Wei, Huanchun and Huang, Teng and Cao, Cong and Peng, Yun and Hu, Xuan},
  title = {Smart Contract Vulnerability Detection Based on Deep Learning and Multimodal Decision Fusion},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {16},
  pages = {7246},
  doi = {10.3390/s23167246}
}
Start for free →