SmartLLMSentry: A Comprehensive LLM Based Smart Contract Vulnerability Detection Framework

Authors : Oualid Zaazaa, Hanan El Bakkali

Pages : 126-137

Doi:10.57019/jmv.1489060

View : 283 | Download : 341

Publication Date : 2024-12-31

Article Type : Research Paper

Abstract :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 LLM-driven rule integration, offering a new approach to improving Blockchain security and addressing previously underexplored vulnerabilities in smart contracts.
Keywords : Smart contract, Vulnerability, Software security, Blockchain, Large Language Models

ORIGINAL ARTICLE URL