一句话：结合微调 LLaMA2 与数据流引导符号执行，自动检测 DApp 前端描述与后端合约实现的不一致。
该论文关注去中心化应用（DApp）中前端宣传功能与后端智能合约实际实现不一致的问题，此类不一致会误导用户并损害 DApp 的可信度。作者首先开展实证研究，归纳出七类不一致，并各以一个真实 DApp 为例。基于此，提出 Hyperion：使用微调后的大语言模型 LLaMA2 解析 DApp 前端描述，提取其宣称的功能，同时对合约字节码进行数据流引导的符号执行以分析实际实现逻辑，最后依据预定义检测模式报告不一致。在包含 54 个 DApp 的基准数据集上，Hyperion 的总体召回率为 84.06%，精确率为 92.06%。作者还将 Hyperion 应用于 835 个真实 DApp，发现其中 459 个至少存在一处不一致，表明该问题在现实世界中较为普遍。
The rapid advancement of blockchain platforms has significantly accelerated the growth of decentralized applications (DApps). Similar to traditional applications, DApps integrate front-end descriptions that showcase their features to attract users, and back-end smart contracts for executing their business logic. However, inconsistencies between the features promoted in front-end descriptions and those actually implemented in the contract can confuse users and undermine DApps's trustworthiness. In this paper, we first conducted an empirical study to identify seven types of inconsistencies, each exemplified by a real-world DApp. Furthermore, we introduce Hyperion, an approach designed to automatically identify inconsistencies between front-end descriptions and back-end code implementation in DApps. This method leverages a fine-tuned large language model LLaMA2 to analyze DApp descriptions and employs dataflow-guided symbolic execution for contract bytecode analysis. Finally, Hyperion reports the inconsistency based on predefined detection patterns. The experiment on our ground truth dataset consisting of 54 DApps shows that Hyperion reaches 84.06% overall recall and 92.06 % overall precision in reporting DApp inconsistencies. We also implement Hyperion to analyze 835 real-world DApps. The experimental results show that Hyperion discovers 459 real-world DApps containing at least one inconsistency.
DOI 原文 ·
@inproceedings{paperbot8885,
title = {Hyperion: Unveiling DApp Inconsistencies Using LLM and Dataflow-Guided Symbolic Execution},
author = {Shuo Yang and Xingwei Lin and Jiachi Chen and Qingyuan Zhong and Lei Xiao and Renke Huang and Yanlin Wang and Zibin Zheng},
booktitle = {ICSE},
year = {2025},
doi = {10.1109/icse55347.2025.00015}
}