arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.02069cs.CRcs.AI
收藏

基于大型语言模型的智能合约审计与LLMBugScanner

Large Language Model based Smart Contract Auditing with LLMBugScanner

Georgia Institute of Technology(佐治亚理工学院)

Yining Yuan, Yifei Wang, Yichang Xu, Zachary Yahn, Sihao Hu, Ling Liu

AI总结:

LLMBugScanner通过结合领域知识适应和集成推理,提升智能合约漏洞检测的鲁棒性和泛化能力,提供了一种高效且可扩展的审计框架。

摘要:

本文提出了LLMBugScanner,一种基于大型语言模型(LLM)的框架,用于通过微调和集成学习检测智能合约漏洞。智能合约审计对LLM提出了几个挑战:不同的预训练模型表现出不同的推理能力,且没有单一模型在所有漏洞类型或合约结构上都能表现一致。这些限制即使在微调单个LLM后仍然存在。为了解决这些挑战,LLMBugScanner结合了领域知识适应与集成推理,以提高鲁棒性和泛化能力。通过领域知识适应,我们对LLM进行微调,以捕捉通用代码语义和指令引导的漏洞推理,使用参数高效调优以减少计算成本。通过集成推理,我们利用多个LLM的互补优势,并应用基于共识的冲突解决策略以产生更可靠的漏洞评估。我们对多个流行的LLM进行了广泛的实验,并将LLMBugScanner与预训练和微调的单个模型进行了比较。结果表明,LLMBugScanner在准确性和泛化能力上均取得了一致的提升,证明了其为智能合约审计提供了一种原理明确、成本效益高且可扩展的框架。

英文摘要:

This paper presents LLMBugScanner, a large language model (LLM) based framework for smart contract vulnerability detection using fine-tuning and ensemble learning. Smart contract auditing presents several challenges for LLMs: different pretrained models exhibit varying reasoning abilities, and no single model performs consistently well across all vulnerability types or contract structures. These limitations persist even after fine-tuning individual LLMs. To address these challenges, LLMBugScanner combines domain knowledge adaptation with ensemble reasoning to improve robustness and generalization. Through domain knowledge adaptation, we fine-tune LLMs on complementary datasets to capture both general code semantics and instruction-guided vulnerability reasoning, using parameter-efficient tuning to reduce computational cost. Through ensemble reasoning, we leverage the complementary strengths of multiple LLMs and apply a consensus-based conflict resolution strategy to produce more reliable vulnerability assessments. We conduct extensive experiments across multiple popular LLMs and compare LLMBugScanner with both pretrained and fine-tuned individual models. Results show that LLMBugScanner achieves consistent accuracy improvements and stronger generalization, demonstrating that it provides a principled, cost-effective, and extensible framework for smart contract auditing.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑