loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Maria Teresa Paratore ; Eda Marchetti and Antonello Calabrò

Affiliation: Institute of Information Science and Technologies “A. Faedo”, National Research Council of Italy (CNR), Pisa, Italy

Keyword(s): Access Control, Artificial Intelligence, Large Language Models, Validation, Cybersecurity.

Abstract: The increasing adoption of generative artificial intelligence, particularly conversational Large Language Models (LLMs), has presented new opportunities for addressing challenges in software development. This paper explores the potential of LLMs in generating eXtensible Access Control Markup Language (XACML) policies. This paper investigates current solutions and strategies for leveraging LLMs to produce verified, secure, compliant access control policies. Specifically, by discussing current methods for enhancing LLM performances in generating structured text, it introduces a pipeline approach that integrates conversational LLMs with syntactic and semantic validators. This approach ensures correctness and reliability of the generated policies. Our proposal is showcased by using real policies and compares various LLMs’ performances (ChatGPT, Claude, Gemini, and LLaMA). Our findings suggest a promising direction for future developments in automated access control policy formulation, br idging the gap between human intent and machine interpretation. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.223.238.183

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Paratore, M. T., Marchetti, E. and Calabrò, A. (2025). From Plain English to XACML Policies: An AI-Based Pipeline Approach. In Proceedings of the 13th International Conference on Model-Based Software and Systems Engineering - MODELSWARD; ISBN 978-989-758-729-0; ISSN 2184-4348, SciTePress, pages 85-96. DOI: 10.5220/0013357200003896

@conference{modelsward25,
author={Maria Teresa Paratore and Eda Marchetti and Antonello Calabrò},
title={From Plain English to XACML Policies: An AI-Based Pipeline Approach},
booktitle={Proceedings of the 13th International Conference on Model-Based Software and Systems Engineering - MODELSWARD},
year={2025},
pages={85-96},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013357200003896},
isbn={978-989-758-729-0},
issn={2184-4348},
}

TY - CONF

JO - Proceedings of the 13th International Conference on Model-Based Software and Systems Engineering - MODELSWARD
TI - From Plain English to XACML Policies: An AI-Based Pipeline Approach
SN - 978-989-758-729-0
IS - 2184-4348
AU - Paratore, M.
AU - Marchetti, E.
AU - Calabrò, A.
PY - 2025
SP - 85
EP - 96
DO - 10.5220/0013357200003896
PB - SciTePress