Generation of Human Comprehensible Access Control Policies from Audit Logs

TL;DR

This paper presents LANTERN, a framework utilizing Large Language Models to automatically generate human-readable access control policies from audit logs, bridging the gap between machine logic and human understanding.

Contribution

It introduces a novel LLM-based framework for translating access logs into natural language policies, enhancing interpretability of complex ABAC systems.

Findings

Effective natural language policy generation demonstrated

Framework scalable to large logs and complex policies

Public web application for reproducibility

Abstract

Over the years, access control systems have become increasingly more complex, often causing a disconnect between what is envisaged by the stakeholders in decision-making positions and the actual permissions granted as evidenced from access logs. For instance, Attribute-based Access Control (ABAC), which is a flexible yet complex model typically configured by system security officers, can be made understandable to others only when presented at a high level in natural language. Although several algorithms have been proposed in the literature for automatic extraction of ABAC rules from access logs, there is no attempt yet to bridge the semantic gap between the machine-enforceable formal logic and human-centric policy intent. Our work addresses this problem by developing a framework that generates human understandable natural language access control policies from logs. We investigate to what extent the power of Large Language Models (LLMs) can be harnessed to achieve both accuracy and scalability in the process. Named LANTERN (LLM-based ABAC Natural Translation and Explanation for Rule Navigation), we have instantiated the framework as a publicly accessible web based application for reproducibility of our results.