SmartLLMSentry: A Comprehensive LLM Based Smart Contract Vulnerability Detection Framework

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zaazaa, Oualid, Bakkali, Hanan El
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912136888844288
author Zaazaa, Oualid
Bakkali, Hanan El
author_facet Zaazaa, Oualid
Bakkali, Hanan El
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_19234
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SmartLLMSentry: A Comprehensive LLM Based Smart Contract Vulnerability Detection Framework
Zaazaa, Oualid
Bakkali, Hanan El
Cryptography and Security
Artificial Intelligence
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.
title SmartLLMSentry: A Comprehensive LLM Based Smart Contract Vulnerability Detection Framework
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2411.19234