Exploring Large Language Models for Access Control Policy Synthesis and Summarization
This work addresses the challenge of error-prone and difficult-to-analyze access control policies for cloud administrators, though it is incremental in leveraging existing LLM capabilities for a specific domain.
The paper tackles the problem of manually writing and analyzing complex access control policies in cloud computing by exploring the use of Large Language Models (LLMs) for policy synthesis and summarization. It finds that LLMs can generate syntactically correct policies but have permissiveness issues, achieving 45.8% equivalence for non-reasoning LLMs and 93.7% for reasoning LLMs, and shows promising results when combined with symbolic approaches for policy analysis.
Cloud computing is ubiquitous, with a growing number of services being hosted on the cloud every day. Typical cloud compute systems allow administrators to write policies implementing access control rules which specify how access to private data is governed. These policies must be manually written, and due to their complexity can often be error prone. Moreover, existing policies often implement complex access control specifications and thus can be difficult to precisely analyze in determining their behavior works exactly as intended. Recently, Large Language Models (LLMs) have shown great success in automated code synthesis and summarization. Given this success, they could potentially be used for automatically generating access control policies or aid in understanding existing policies. In this paper, we explore the effectiveness of LLMs for access control policy synthesis and summarization. Specifically, we first investigate diverse LLMs for access control policy synthesis, finding that: although LLMs can effectively generate syntactically correct policies, they have permissiveness issues, generating policies equivalent to the given specification 45.8% of the time for non-reasoning LLMs, and 93.7% of the time for reasoning LLMs. We then investigate how LLMs can be used to analyze policies by introducing a novel semantic-based request summarization approach which leverages LLMs to generate a precise characterization of the requests allowed by a policy. Our results show that while there are significant hurdles in leveraging LLMs for automated policy generation, LLMs show promising results when combined with symbolic approaches in analyzing existing policies.