An AI-Based Control Framework for Secure and Compliant Linux Systems in Financial Services
Main Article Content
Abstract
Financial services organizations rely extensively on enterprise Linux systems to support critical workloads such as payment processing, customer data management, trading platforms, and regulatory reporting. These systems must operate under strict security and compliance requirements while remaining highly available and adaptable to continuous operational change. Traditional control and compliance mechanisms for Linux environments are often based on static policies, manual audits, and periodic assessments, which struggle to provide real-time assurance in large and dynamic infrastructures.
This paper proposes an AI-based control framework for secure and compliant Linux systems in financial services environments. The framework integrates declarative control definitions, continuous system state validation, and AI-assisted control analysis to enhance governance effectiveness. Control definitions are expressed as code and continuously evaluated against runtime system behavior, while AI-based analysis identifies recurring control violations, prioritizes risks based on operational and regulatory impact, and reduces non-actionable findings.
Through architectural design and controlled evaluation in enterprise Linux environments aligned with financial services operational patterns, the study demonstrates that AI-assisted control frameworks improve compliance visibility, reduce configuration drift, and support more efficient governance decision-making. The results indicate that AI-based analysis, when applied as decision support rather than autonomous enforcement, can strengthen security and compliance outcomes while preserving transparency, auditability, and human oversight.