面向代码的LLM安全卫士
LLM Security Guard for Code
AI总结:
本文提出开源框架LLMSecGuard,通过结合静态代码分析器与LLMs来增强代码安全性,并提供基准测试功能以评估模型安全属性的演变。
摘要:
许多开发人员依赖大型语言模型(LLMs)来促进软件开发。然而,这些模型在安全领域表现出的能力有限。我们引入了LLMSecGuard,这是一个通过静态代码分析器与LLMs之间的协同作用来提供增强代码安全性的框架。LLMSecGuard是开源的,旨在为开发人员提供比LLMs最初生成的代码更安全的代码解决方案。该框架还具有基准测试功能,旨在提供对这些模型不断演变的安全属性的洞察。
英文摘要:
Many developers rely on Large Language Models (LLMs) to facilitate software development. Nevertheless, these models have exhibited limited capabilities in the security domain. We introduce LLMSecGuard, a framework to offer enhanced code security through the synergy between static code analyzers and LLMs. LLMSecGuard is open source and aims to equip developers with code solutions that are more secure than the code initially generated by LLMs. This framework also has a benchmarking feature, aimed at providing insights into the evolving security attributes of these models.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。