.png){kind=icon}
.png){kind=icon}
Return
CodeSpeak: Improving smart contract vulnerability detection via LLM-assisted code analysis
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jss.2025.112635.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A framework assisted by large language models for smart contract vulnerability detection. • Mimicry of expert security audit practices through domain-specific prompts. • Integration of code analysis and prompt learning for vulnerability detection. • Performance improvements over state-of-the-art methods across four vulnerability types.
Journal
IF:
4.1
Papers:
5.4K
Citations:
8.4K