BriefGPT.xyz
May, 2024
利用大型语言模型进行软件漏洞检测:综合基准研究
Harnessing Large Language Models for Software Vulnerability Detection: A Comprehensive Benchmarking Study
HTML
PDF
Karl Tamberg, Hayretdin Bahsi
TL;DR
通过使用大型语言模型(LLMs)来辅助发现源代码中的漏洞,相比传统的静态分析工具,我们发现LLMs能够找出更多问题,提高漏洞检测的回溯率和F1分数,从而使得代码更加安全。
Abstract
Despite various approaches being employed to detect
vulnerabilities
, the number of reported
vulnerabilities
shows an upward trend over the years. This suggests the problems are not caught before the code is relea
→