Work

MOS: Towards Effective Smart Contract Vulnerability Detection through Mixture-of-Experts Tuning of Large Language Models

Year: 2024

Type: article

Abstract: This is dataset and source code for 'MOS'. MOS is a smart contract vulnerability detection framework based on mixture-of-experts tuning of large language models. The framework features three key innovations: continual pre-training on smart contract datasets, a MOE-Tuning dataset construction pipeline combining LLM generation with expert verification, and a vulnerability-aware routing mechanism directing analysis to specialized expert networks. This design aims to overcome the limitations of existing methods while providing reliable vulnerability detection and explanations.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.14568588

Author: Anonymous

Language: English

Topic: Blockchain Technology Applications and Security

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W6911821688

FWCI:

Cites:

Cited by:

Related to: