Combining Graph Neural Networks with Expert Knowledge for Smart Contract Vulnerability Detection

Liu，Zhenguang1; Qian，Peng2; Wang，Xiaoyang3; Zhuang，Yuan4; Qiu，Lin5; Wang，Xun6

2021

10.1109/TKDE.2021.3095196

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING   影响因子和分区

1041-4347

1558-2191

Smart contract vulnerability detection draws extensive attention in recent years due to the substantial losses caused by hacker-attacks. Existing efforts for contract security analysis heavily rely on rigid rules defined by experts, which is labor-intensive and non-scalable. More importantly, expert-defined rules tend to be error-prone and suffer the inherent risk of being cheated by crafty attackers. Recent researches focus on the symbolic execution and formal analysis of smart contract for vulnerability detection, yet to achieve a precise and scalable solution. Although several methods have been proposed to detect vulnerabilities in smart contracts, there is still a lack of effort that considers combining expert-defined security patterns with deep neural networks. In this paper, we explore using graph neural networks and expert knowledge for smart contract vulnerability detection. Specifically, we cast the rich control- and data- flow semantics of the source code into a contract graph. Then, we propose a novel temporal message propagation network to extract graph feature from the normalized graph, and combine the graph feature with expert patterns to yield a final detection system. Extensive experiments are conducted on all the smart contracts that have source code in two platforms. Empirical results show significant accuracy improvements over state-of-the-art methods.

blockchain Blockchain Computer bugs Deep learning expert knowledge Feature extraction Knowledge engineering Security Semantics smart contract Smart contracts vulnerability detection

EI ; SCI

英语

其他

Natural Science Founda-tion of Zhejiang Province[LQ19F020001] ; National Natural Science Foundation of China["61902348","61802345"] ; Research Programof Zhejiang Lab[2019KD0AC02]

Computer Science ; Engineering

Computer Science, Artificial Intelligence ; Computer Science, Information Systems ; Engineering, Electrical & Electronic

WOS:000914161200015

IEEE COMPUTER SOC

20213210744754

Backpropagation ; Data flow analysis ; Deep neural networks ; Flow graphs ; Personal computing ; Semantics

Artificial Intelligence:723.4 ; Computer Applications:723.5 ; Combinatorial Mathematics, Includes Graph Theory, Set Theory:921.4

ENGINEERING

2-s2.0-85109397423

Scopus

1.School of computer and information engineering, Zhejiang Gongshang University, 12625 Hangzhou, Zhejiang, China, (e-mail: liuzhenguang2008@gmail.com)
2.School of Computer and Information Engineering, Zhejiang Gongshang University, 12625 Hangzhou, Zhejiang, China, (e-mail: messi.qp711@gmail.com)
3.School of Computer and Information Engineering, Zhejiang Gongshang University, 12625 Hangzhou, Zhejiang, China, (e-mail: xiaoyangw@zjgsu.edu.cn)
4.School of Computing, National University of Singapore, 37580 Singapore, Singapore, Singapore, (e-mail: zhuangyuan2020@outlook.com)
5.Department of Computer Science and Engineering, Southern University of Science and Technology, 255310 Shenzhen, Guangdong, China, (e-mail: lin_qiu@u.nus.edu)
6.School of Computer Science and Information Engineering, Zhejiang Gongshang University, 12625 Hangzhou, Zhejiang, China, (e-mail: xwang@zjgsu.edu.cn)

Liu，Zhenguang,Qian，Peng,Wang，Xiaoyang,et al. Combining Graph Neural Networks with Expert Knowledge for Smart Contract Vulnerability Detection[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2021,PP(99):1-1.

Liu，Zhenguang,Qian，Peng,Wang，Xiaoyang,Zhuang，Yuan,Qiu，Lin,&Wang，Xun.(2021).Combining Graph Neural Networks with Expert Knowledge for Smart Contract Vulnerability Detection.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,PP(99),1-1.

Liu，Zhenguang,et al."Combining Graph Neural Networks with Expert Knowledge for Smart Contract Vulnerability Detection".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING PP.99(2021):1-1.