ContractTinker: LLM-Empowered Vulnerability Repair for Real-World Smart Contracts

TL;DR

This work proposes ContractTinker, a Large Language Models-empowered tool for real-world vulnerability repair, and adopts the Chain-of-Thought approach to break down the entire generation task into sub-tasks to reduce hallucination.

Abstract

Smart contracts are susceptible to being exploited by attackers, especially when facing real-world vulnerabilities. To mitigate this risk, developers often rely on third-party audit services to identify potential vulnerabilities before project deployment. Nevertheless, repairing the identified vulnerabilities is still complex and labor-intensive, particularly for developers lacking security expertise. Moreover, existing pattern-based repair tools mostly fail to address real-world vulnerabilities due to their lack of high-level semantic understanding. To fill this gap, we propose ContractTinker, a Large Language Models (LLMs)-empowered tool for real-world vulnerability repair. The key insight is our adoption of the Chain-of-Thought approach to break down the entire generation task into sub-tasks. Additionally, to reduce hallucination, we integrate program static analysis to guide the LLM. We evaluate ContractTinker on 48 high-risk vulnerabilities. The experimental results show that among the patches generated by ContractTinker, 23 (48%) are valid patches that fix the vulnerabilities, while 10 (21%) require only minor modifications. A video of ContractTinker is available at https://youtu.be/HWFVi-YHcPE.

Figures (3)

• Figure 1: Workflow of ContractTinker
• Figure 2: Prompt Design of ContractTinker
• Figure 3: The Screenshot of ContractTinker