Large Language Model based Smart Contract Auditing with LLMBugScanner

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yuan, Yining, Wang, Yifei, Xu, Yichang, Yahn, Zachary, Hu, Sihao, Liu, Ling
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917117588144128
author Yuan, Yining
Wang, Yifei
Xu, Yichang
Yahn, Zachary
Hu, Sihao
Liu, Ling
author_facet Yuan, Yining
Wang, Yifei
Xu, Yichang
Yahn, Zachary
Hu, Sihao
Liu, Ling
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_02069
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Large Language Model based Smart Contract Auditing with LLMBugScanner
Yuan, Yining
Wang, Yifei
Xu, Yichang
Yahn, Zachary
Hu, Sihao
Liu, Ling
Cryptography and Security
Artificial Intelligence
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.
title Large Language Model based Smart Contract Auditing with LLMBugScanner
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2512.02069