Abstract

As cloud databases continue to gain widespread adoption, ensuring data security remains a critical challenge due to risks such as unauthorized access, data breaches, and insider threats. Traditional encryption techniques provide data confidentiality but lack the flexibility needed for dynamic and fine-grained access control. Attribute-Based Encryption (ABE) offers a robust solution by enabling access control based on user attributes rather than static roles, ensuring that only authorized users with matching attributes can decrypt sensitive data. This review explores the integration of Artificial Intelligence (AI) with ABE to enhance the security and efficiency of cloud database protection. Our approach leverages Ciphertext-Policy ABE (CP-ABE) to enforce access control policies while utilizing AI for real-time anomaly detection, adaptive authentication, and automated encryption policy updates. Machine learning algorithms analyze user behavior patterns to detect potential threats, such as unauthorized access attempts or suspicious data usage, enabling proactive security responses. AI-driven risk scoring further enhances access management by dynamically adjusting encryption policies based on user trust levels. The proposed framework is evaluated through a case study in a cloud environment, demonstrating improved security, reduced unauthorized access risks, and enhanced scalability compared to conventional encryption models. Performance analysis highlights the feasibility of AI-assisted ABE despite computational overhead, with optimizations improving efficiency for real-world applications. By combining AI-driven analytics and advanced cryptographic techniques, this study presents a novel approach to securing cloud databases while maintaining data confidentiality and regulatory compliance. Future research will focus on improving scalability, integrating federated learning for decentralized security, and enhancing AI-driven policy automation.