Mining Frequency Features for On-Chain Smart Contract Vulnerability Multi-Class Classification

Abstract

Due to the immutable nature of blockchain, vulnerability detection in on-chain smart contracts is imperative to ensure the security of blockchain transaction. As smart contracts automate significant financial and operational transactions, detecting vulnerabilities before they are exploited is critical. Recently, the application of machine learning techniques to this domain has increased, primarily due to their powerful feature extraction capabilities and operational efficiency in detecting anomalies. Considerable efforts in past research have focused on mining semantic and syntactic features from off-chain source code of smart contracts, typically written in high-level languages like Solidity. However, on-chain smart contracts, which are represented in the form of opcodes, lack these high-level semantic features. This absence necessitates different approaches for effective vulnerability detection. Although on-chain smart contracts lack high-level semantic features, the limited number of characters in opcodes results in more distinct frequency patterns of code. Therefore, in this paper, we explore a multi-class vulnerability detection approach based on the frequency features of smart contract opcodes. This paper provides a simple yet effective feature embedding method for on-chain opcode contract. Experiments on both binary and multi-class vulnerability detection tasks have been conducted to validate its scalability and effectiveness.