使用大型语言模型合成访问控制策略
Synthesizing Access Control Policies using Large Language Models
AI总结：
本文研究零样本提示 LLM 从请求列表或自然语言描述合成 IAM 访问控制策略，提出基于语法的结构化提示方法并通过初步实验验证其有效性。
摘要：
云计算系统允许管理员编写用于管控私有数据访问的访问控制策略。尽管策略使用便捷的语言编写，例如 AWS Identity and Access Management Policy Language，但手动编写的策略往往变得复杂且容易出错。本文研究大型语言模型（LLM）能否以及在多大程度上可用于合成访问控制策略。研究聚焦于以下任务：给定访问控制请求规范，并通过零样本提示 LLM 合成格式良好、能够正确遵循该请求规范的访问控制策略。作者考虑了两种场景：其一，请求规范以具体的允许或拒绝请求列表给出；其二，使用自然语言描述来指定需要允许或拒绝的请求集合。随后，作者论证了对于零样本提示而言，采用基于语法的方法来获得更精确、更结构化的提示是必要的，并通过实验给出了验证该方法的初步结果。
英文摘要：
Cloud compute systems allow administrators to write access control policies that govern access to private data. While policies are written in convenient languages, such as AWS Identity and Access Management Policy Language, manually written policies often become complex and error prone. In this paper, we investigate whether and how well Large Language Models (LLMs) can be used to synthesize access control policies. Our investigation focuses on the task of taking an access control request specification and zero-shot prompting LLMs to synthesize a well-formed access control policy which correctly adheres to the request specification. We consider two scenarios, one which the request specification is given as a concrete list of requests to be allowed or denied, and another in which a natural language description is used to specify sets of requests to be allowed or denied. We then argue that for zero-shot prompting, more precise and structured prompts using a syntax based approach are necessary and experimentally show preliminary results validating our approach.
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。
