Synthesizing Access Control Policies using Large Language Models
This addresses the challenge for cloud administrators of reducing errors in access control policies, though it appears incremental as it builds on existing LLM capabilities for a specific domain.
The paper tackles the problem of manually writing complex and error-prone access control policies for cloud systems by investigating the use of Large Language Models (LLMs) to synthesize these policies from specifications, showing preliminary results that validate a syntax-based prompting approach for improved accuracy.
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.