Leveraging RAG and LLMs for Access Control Policy Extraction From User Stories in Agile Software Development

Agile development has become increasingly popular among software development teams due to its capacity to deliver and update software rapidly while accommodating evolving requirements. Within this dynamic context, access control policies are critical for ensuring the security of systems by defining...

Full description

Saved in:
Bibliographic Details
Main Authors: Sara Aboukadri, Aafaf Ouaddah, Abdellatif Mezrioui, Ikram El Asri
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11071540/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849319805012672512
author Sara Aboukadri
Aafaf Ouaddah
Abdellatif Mezrioui
Ikram El Asri
author_facet Sara Aboukadri
Aafaf Ouaddah
Abdellatif Mezrioui
Ikram El Asri
author_sort Sara Aboukadri
collection DOAJ
description Agile development has become increasingly popular among software development teams due to its capacity to deliver and update software rapidly while accommodating evolving requirements. Within this dynamic context, access control policies are critical for ensuring the security of systems by defining who can access specific resources under given conditions. However, identifying and documenting these policies often rely on manual, time-intensive processes prone to errors and oversight. This paper proposes an innovative framework leveraging Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) to automate the extraction and organization of access control policies from user stories and software documentation. The framework focuses on the early stages of the development lifecycle, capturing access control requirements as expressed in natural language artifacts. It comprises two core components: 1) a pipeline for extracting and categorizing access control policies, enabling precise mappings between roles, actions, and resources, and 2) an interactive chatbot designed to support Security Operations Center (SOC) analysts in evaluating suspicious access requests by providing contextualized insights into access policies. By integrating advanced natural language processing techniques with retrieval-based augmentation, the framework aims to reinforce access control mechanisms by improving visibility, and providing contextualized insights for security analysts.
format Article
id doaj-art-cda86631d57a4d3683cfed1e5b1dcbf7
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-cda86631d57a4d3683cfed1e5b1dcbf72025-08-20T03:50:20ZengIEEEIEEE Access2169-35362025-01-011311646211647210.1109/ACCESS.2025.358620311071540Leveraging RAG and LLMs for Access Control Policy Extraction From User Stories in Agile Software DevelopmentSara Aboukadri0https://orcid.org/0000-0003-4589-4178Aafaf Ouaddah1Abdellatif Mezrioui2https://orcid.org/0000-0003-4731-355XIkram El Asri3https://orcid.org/0000-0001-5272-8587STRS Laboratory/CEDOC 2TI, National Institute of Posts and Telecommunications, Rabat, MoroccoSTRS Laboratory/CEDOC 2TI, National Institute of Posts and Telecommunications, Rabat, MoroccoSTRS Laboratory/CEDOC 2TI, National Institute of Posts and Telecommunications, Rabat, MoroccoSTRS Laboratory/CEDOC 2TI, National Institute of Posts and Telecommunications, Rabat, MoroccoAgile development has become increasingly popular among software development teams due to its capacity to deliver and update software rapidly while accommodating evolving requirements. Within this dynamic context, access control policies are critical for ensuring the security of systems by defining who can access specific resources under given conditions. However, identifying and documenting these policies often rely on manual, time-intensive processes prone to errors and oversight. This paper proposes an innovative framework leveraging Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) to automate the extraction and organization of access control policies from user stories and software documentation. The framework focuses on the early stages of the development lifecycle, capturing access control requirements as expressed in natural language artifacts. It comprises two core components: 1) a pipeline for extracting and categorizing access control policies, enabling precise mappings between roles, actions, and resources, and 2) an interactive chatbot designed to support Security Operations Center (SOC) analysts in evaluating suspicious access requests by providing contextualized insights into access policies. By integrating advanced natural language processing techniques with retrieval-based augmentation, the framework aims to reinforce access control mechanisms by improving visibility, and providing contextualized insights for security analysts.https://ieeexplore.ieee.org/document/11071540/Access controlagile software developmentsoftware requirementsRAGLLMs
spellingShingle Sara Aboukadri
Aafaf Ouaddah
Abdellatif Mezrioui
Ikram El Asri
Leveraging RAG and LLMs for Access Control Policy Extraction From User Stories in Agile Software Development
IEEE Access
Access control
agile software development
software requirements
RAG
LLMs
title Leveraging RAG and LLMs for Access Control Policy Extraction From User Stories in Agile Software Development
title_full Leveraging RAG and LLMs for Access Control Policy Extraction From User Stories in Agile Software Development
title_fullStr Leveraging RAG and LLMs for Access Control Policy Extraction From User Stories in Agile Software Development
title_full_unstemmed Leveraging RAG and LLMs for Access Control Policy Extraction From User Stories in Agile Software Development
title_short Leveraging RAG and LLMs for Access Control Policy Extraction From User Stories in Agile Software Development
title_sort leveraging rag and llms for access control policy extraction from user stories in agile software development
topic Access control
agile software development
software requirements
RAG
LLMs
url https://ieeexplore.ieee.org/document/11071540/
work_keys_str_mv AT saraaboukadri leveragingragandllmsforaccesscontrolpolicyextractionfromuserstoriesinagilesoftwaredevelopment
AT aafafouaddah leveragingragandllmsforaccesscontrolpolicyextractionfromuserstoriesinagilesoftwaredevelopment
AT abdellatifmezrioui leveragingragandllmsforaccesscontrolpolicyextractionfromuserstoriesinagilesoftwaredevelopment
AT ikramelasri leveragingragandllmsforaccesscontrolpolicyextractionfromuserstoriesinagilesoftwaredevelopment