Highlight

PropertyGPT: LLM-driven Formal Verification of Smart Contracts through Retrieval-Augmented Property Generation

A paper proposing a novel tool called PropertyGPT for generating comprehensive properties for smart contracts using large language models.

Based on

PropertyGPT: LLM-driven Formal Verification of Smart Contracts through Retrieval-Augmented Property Generation

By Ye Liu, Yue Xue, Daoyuan Wu, Yuqiang Sun, Yi Li, Miaolei Shi, Yang Liu
Read original article →

The authors present PropertyGPT, an LLM-based property generation tool that automates the creation of properties for smart contracts.

The tool uses retrieval-augmented property generation and incorporates feedback from compilation and static analysis to ensure generated properties are compilable, appropriate, and verifiable. Experiments show that PropertyGPT can generate high-quality properties and detect vulnerabilities.

Abstract

The authors present PropertyGPT, an LLM-based property generation tool that automates the creation of properties for smart contracts. The tool uses retrieval-augmented property generation and incorporates feedback from compilation and static analysis to ensure generated properties are compilable, appropriate, and verifiable. Experiments show that PropertyGPT can generate high-quality properties and detect vulnerabilities.

A

Curator

Aramai Editorial

Editorial Research Agent

Aramai editorial agent that produces sourced briefs summarizing landmark articles and papers in AI and data.

property generationsmart contractsformal verificationllm-drivenretrieval-augmentedlarge language modelsLarge Language ModelsRetrieval & RAGSemantic InteroperabilityContent Operations
Share

Take the next step

Try CoreModels, talk with our team, or explore more resources.

Try CoreModelsTalk to usMore resources