Validating Smart Contracts Using GPT Assistant

Xianhao Zhang, Zhiyuan Wei, Jing Sun, Zijian Zhang, Zixiao Zhao

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper presents SCareGPT, an advanced smart contract auditing tool that harnesses domain-specific GPT Assistant technology to enhance vulnerability detection and analysis. We created a standardized dataset featuring 100 labeled vulnera-ble smart contracts and performed comparative benchmarks between SCareGPT and ten traditional smart contract vulnerability detection tools. Our findings demonstrate that SCareGPT excels beyond these competitors in the majority of assessed vulnerability categories, affirming its superiority and utility in the rapidly evolving domain of smart contract security.

Original languageEnglish
Title of host publicationProceedings - 2024 IEEE 48th Annual Computers, Software, and Applications Conference, COMPSAC 2024
EditorsHossain Shahriar, Hiroyuki Ohsaki, Moushumi Sharmin, Dave Towey, AKM Jahangir Alam Majumder, Yoshiaki Hori, Ji-Jiang Yang, Michiharu Takemoto, Nazmus Sakib, Ryohei Banno, Sheikh Iqbal Ahamed
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1564-1565
Number of pages2
ISBN (Electronic)9798350376968
DOIs
Publication statusPublished - 2024
Event48th IEEE Annual Computers, Software, and Applications Conference, COMPSAC 2024 - Osaka, Japan
Duration: 2 Jul 20244 Jul 2024

Publication series

NameProceedings - 2024 IEEE 48th Annual Computers, Software, and Applications Conference, COMPSAC 2024

Conference

Conference48th IEEE Annual Computers, Software, and Applications Conference, COMPSAC 2024
Country/TerritoryJapan
CityOsaka
Period2/07/244/07/24

Keywords

  • GPT
  • Smart contract
  • Vulnerability detection

Fingerprint

Dive into the research topics of 'Validating Smart Contracts Using GPT Assistant'. Together they form a unique fingerprint.

Cite this