Smart Contract Vulnerability Detection Based on Deep Learning and Multimodal Decision Fusion
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,...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/16/7246 |
| _version_ | 1797583217981652992 |
|---|---|
| author | Weichu Deng Huanchun Wei Teng Huang Cong Cao Yun Peng Xuan Hu |
| author_facet | Weichu Deng Huanchun Wei Teng Huang Cong Cao Yun Peng Xuan Hu |
| author_sort | Weichu Deng |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T23:35:45Z |
| format | Article |
| id | doaj.art-84a346f7474e40e6bbaf0f61c056bf23 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T23:35:45Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-84a346f7474e40e6bbaf0f61c056bf232023-11-19T02:58:54ZengMDPI AGSensors1424-82202023-08-012316724610.3390/s23167246Smart Contract Vulnerability Detection Based on Deep Learning and Multimodal Decision FusionWeichu Deng0Huanchun Wei1Teng Huang2Cong Cao3Yun Peng4Xuan Hu5Institute of Artificial Intelligence and Blockchain, Guangzhou University, Guangzhou 510006, ChinaSchool of Beidou, Guangxi University of Information Engineering, Nanning 530299, ChinaInstitute of Artificial Intelligence and Blockchain, Guangzhou University, Guangzhou 510006, ChinaInstitute of Artificial Intelligence and Blockchain, Guangzhou University, Guangzhou 510006, ChinaInstitute of Artificial Intelligence and Blockchain, Guangzhou University, Guangzhou 510006, ChinaInformation Security Research Center, CEPREI Laboratory, Guangzhou 510610, ChinaWith 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.https://www.mdpi.com/1424-8220/23/16/7246multimodal fusionsmart contractvulnerability detectiondeep learning |
| spellingShingle | Weichu Deng Huanchun Wei Teng Huang Cong Cao Yun Peng Xuan Hu Smart Contract Vulnerability Detection Based on Deep Learning and Multimodal Decision Fusion Sensors multimodal fusion smart contract vulnerability detection deep learning |
| title | Smart Contract Vulnerability Detection Based on Deep Learning and Multimodal Decision Fusion |
| title_full | Smart Contract Vulnerability Detection Based on Deep Learning and Multimodal Decision Fusion |
| title_fullStr | Smart Contract Vulnerability Detection Based on Deep Learning and Multimodal Decision Fusion |
| title_full_unstemmed | Smart Contract Vulnerability Detection Based on Deep Learning and Multimodal Decision Fusion |
| title_short | Smart Contract Vulnerability Detection Based on Deep Learning and Multimodal Decision Fusion |
| title_sort | smart contract vulnerability detection based on deep learning and multimodal decision fusion |
| topic | multimodal fusion smart contract vulnerability detection deep learning |
| url | https://www.mdpi.com/1424-8220/23/16/7246 |
| work_keys_str_mv | AT weichudeng smartcontractvulnerabilitydetectionbasedondeeplearningandmultimodaldecisionfusion AT huanchunwei smartcontractvulnerabilitydetectionbasedondeeplearningandmultimodaldecisionfusion AT tenghuang smartcontractvulnerabilitydetectionbasedondeeplearningandmultimodaldecisionfusion AT congcao smartcontractvulnerabilitydetectionbasedondeeplearningandmultimodaldecisionfusion AT yunpeng smartcontractvulnerabilitydetectionbasedondeeplearningandmultimodaldecisionfusion AT xuanhu smartcontractvulnerabilitydetectionbasedondeeplearningandmultimodaldecisionfusion |