用大模型自动生成符合需求的云访问控制策略，减少人工出错。
Synthesizing Access Control Policies using Large Language Models
- 通过结构化提示词引导大模型生成合规策略
- 在自然语言和具体请求两种场景下均验证有效
- 适合需要快速生成安全策略的运维人员
云计算系统允许管理员编写访问控制策略以管理对私有数据的访问。尽管策略使用便捷语言（如 AWS IAM 策略语言）编写，但手动编写常导致策略复杂且易出错。本文研究大语言模型（LLM）在自动生成访问控制策略方面的可行性和效果。聚焦于：给定访问请求规范，通过零样本提示让 LLM 生成格式正确且符合规范的策略。考虑两种场景：一是提供具体的需允许或拒绝的请求列表；二是用自然语言描述需允许或拒绝的请求集合。研究指出，对于零样本提示，采用基于语法的更精确、结构化提示更为必要，并通过实验验证了该方法的初步有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。