NLACP Dataset Expansion With AI: Leveraging ChatGPT for Policy Generation

Natural Language Access Control Policies (NLACPs) play a pivotal role in access control systems, yet the scarcity of high-quality public datasets severely hinders advancements in NLP/ML-driven policy automation. Existing datasets, constrained by labor-intensive manual curation, confidentiality barriers, and rigid synthesis methods, suffer from limited scale, semantic inconsistency, and poor adaptability to emerging domains such as Smart Healthcare and the Internet of Vehicles. To address this critical gap, we proposeGenPy, a novel framework leveraging large language models (LLMs) like ChatGPT and domain-specific knowledge graphs to systematically generate scalable, semantically rich NLACPs datasets.GenPypioneers the integration of LLMs into NLACPs synthesis, offering three core innovations: (1) A generation module combining knowledge graphs with prompt engineering to produce diverse, domain-aligned policies; (2) An annotation module employing few-shot learning to filter non-policy statements and ensure quality; (3) A policy management module resolving redundancies and conflicts while enabling conflict injection for optimization research. By embedding domain semantics (e.g., Internet of Vehicles compliance with automotive data laws),GenPyenriches traditional datasets and supports fine-grained policy requirements. Experiments demonstrate thatGenPygenerates 5,000+ high-quality NLACPs across multiple domains, achieving an F1 score of exceeding 93% in NLACPs classification tasks. Notably, augmenting the classification models in RAGent withGenPy-generated data improves NLACPs classification accuracy by 2-9%, validating its practical utility. Our work establishes the first LLM-based pipeline that integrates knowledge graphs with customizable prompts to generate semantically rich NLACPs, supporting fine-grained access control models, NLACPs identification, and policy management across diverse security requirements. We providing an open-source repository of policies, code, and technical frameworks to catalyze future research in access control automation. The dataset and implementation are publicly available at https://github.com/fe1w0/NLACP-LLM.