DEVELOPMENT OF AN AI-ENHANCED SMART ROLE ASSIGNMENT AND AUDIT TRAIL MODEL FOR SECURE ENTERPRISE INFORMATION SYSTEMS

Abstract

Enterprise information systems face increasing challenges in managing user access and ensuring cybersecurity compliance. Traditional Role-Based Access Control (RBAC) models are often static, requiring manual intervention and lacking intelligent monitoring capabilities. This study proposes an AI-enhanced Smart Role Assignment and Audit Trail Model, integrating machine learning algorithms with RBAC and comprehensive audit logs. The system dynamically recommends user roles, records all user actions, and proactively detects anomalies, enhancing security and operational efficiency. The methodology adopted involved system design and development using ASP.NET (C#) and MS SQL Server, combined with experimental evaluation using simulated enterprise data. The simulated dataset included 1,000 users across 10 modules with historical access logs. Performance metrics such as role assignment accuracy, audit coverage, administrative efficiency, and anomaly detection were measured to assess the system’s effectiveness. Results demonstrated improved role assignment accuracy (93.5%), audit coverage (98%), and a 77% reduction in administrative effort compared to traditional RBAC systems. The findings indicate that AI-enhanced RBAC with intelligent audit trails can significantly improve security, traceability, and operational efficiency in enterprise environments.