@Article{cmes.2025.062902,
AUTHOR = {Sondes Baccouri, Takoua Abdellatif},
TITLE = {BIG-ABAC: Leveraging Big Data for Adaptive, Scalable, and Context-Aware Access Control},
JOURNAL = {Computer Modeling in Engineering \& Sciences},
VOLUME = {143},
YEAR = {2025},
NUMBER = {1},
PAGES = {1071--1093},
URL = {http://www.techscience.com/CMES/v143n1/60478},
ISSN = {1526-1506},
ABSTRACT = {Managing sensitive data in dynamic and high-stakes environments, such as healthcare, requires access control frameworks that offer real-time adaptability, scalability, and regulatory compliance. <b>BIG-ABAC</b> introduces a transformative approach to Attribute-Based Access Control (ABAC) by integrating real-time policy evaluation and contextual adaptation. Unlike traditional ABAC systems that rely on static policies, BIG-ABAC dynamically updates policies in response to evolving rules and real-time contextual attributes, ensuring precise and efficient access control. Leveraging decision trees evaluated in real-time, BIG-ABAC overcomes the limitations of conventional access control models, enabling seamless adaptation to complex, high-demand scenarios. The framework adheres to the <b>NIST ABAC standard</b> while incorporating modern distributed streaming technologies to enhance <b>scalability and traceability</b>. Its flexible policy enforcement mechanisms facilitate the implementation of regulatory requirements such as HIPAA and GDPR, allowing organizations to align access control policies with compliance needs dynamically. Performance evaluations demonstrate that BIG-ABAC processes <b>95%</b> of access requests within <b>50 ms</b> and updates policies dynamically with a latency of <b>30 ms</b>, significantly outperforming traditional ABAC models. These results establish BIG-ABAC as a benchmark for <b>adaptive, scalable, and context-aware</b> access control, making it an ideal solution for dynamic, high-risk domains such as healthcare, smart cities, and Industrial IoT (IIoT).},
DOI = {10.32604/cmes.2025.062902}
}