SmartLLMSentry: A Comprehensive LLM Based Smart Contract Vulnerability Detection Framework
This addresses security for blockchain developers by enhancing detection speed and accuracy, though it appears incremental as it builds on existing LLM methods for a specific domain.
The paper tackled smart contract vulnerability detection by introducing SmartLLMSentry, a framework using ChatGPT with in-context training, achieving 91.1% exact match accuracy in detecting five vulnerabilities.
Smart contracts are essential for managing digital assets in blockchain networks, highlighting the need for effective security measures. This paper introduces SmartLLMSentry, a novel framework that leverages large language models (LLMs), specifically ChatGPT with in-context training, to advance smart contract vulnerability detection. Traditional rule-based frameworks have limitations in integrating new detection rules efficiently. In contrast, SmartLLMSentry utilizes LLMs to streamline this process. We created a specialized dataset of five randomly selected vulnerabilities for model training and evaluation. Our results show an exact match accuracy of 91.1% with sufficient data, although GPT-4 demonstrated reduced performance compared to GPT-3 in rule generation. This study illustrates that SmartLLMSentry significantly enhances the speed and accuracy of vulnerability detection through LLMdriven rule integration, offering a new approach to improving Blockchain security and addressing previously underexplored vulnerabilities in smart contracts.