Similarity Measure for Smart Contract Bytecode Based on CFG Feature Extraction

Abstract

As the mainstream of smart contract research, most Ethereum smart contracts do not open their source code, and the bytecode of smart contracts has attracted the attention of researchers. Based on the similarity measurement of smart contract bytecode, a series of tasks such as vulnerability mining, contract upgrading and malicious contract detection can be carried out. This paper proposes a method to measure the similarity of smart contract bytecode. Firstly, the key opcode combination of smart contract is summarized. When traversing the CFG(control flow graph) constructed by decompilation of smart contract bytecode, the opcodes in the basic block are pattern matched, and the features between the basic blocks are extracted according to the in-out degree, so as to enhance the similarity measurement effect of contract semantics in vector space. The experimental results show that the proposed method is greatly improved compared with the baseline.