VulnScan GPT: a new framework for smart contract vulnerability detection combining vector database and GPT model
Year: 2024
Type: article
Abstract: With the rapid development of blockchain technology and smart contracts, the security issues of smart contracts have become increasingly serious. To address the significant limitations of traditional detection methods in handling the complexity and scale of smart contracts, a new framework for smart contract vulnerability detection that combines a vector database and a generative pre-trained transformer (GPT) model — VulnScan GPT — has been proposed. This framework comprises three main components: function signature extraction, vector database storage and retrieval, and GPT-based vulnerability detection. The framework uses the solc tool to generate an abstract syntax tree from smart contracts, extract function signatures, and vectorize the code for storage. By integrating the GPT model, the framework can preliminarily analyze and filter key functions based on common vulnerability scenarios and then retrieve relevant implementations from the vector database for in-depth assessment. This method gradually optimizes function analysis through an iterative detection mechanism, leveraging the efficient storage and retrieval capabilities of the vector database, combined with the deep natural language processing abilities of the GPT model, enhancing the accuracy and comprehensiveness of vulnerability detection. In the experimental evaluation, tests were conducted on various datasets to detect automated market maker price manipulation and initial risk deposit vulnerabilities, demonstrating that VulnScan GPT not only improves the accuracy of vulnerability detection, but also significantly reduces operational costs by optimizing token usage, resulting in an efficient and cost-effective detection solution.
Authors: Lianjie Wang, Yunhao Zhao, Keqing Wang, Zhongwen Zhang, Wenyin Zhang
Institution: Linyi University
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4405919385