Artificial Intelligence Techniques for Secure Cloud Data Storage and Retrieval Using Giant Trevally Optimizer with Quantum Convolutional Neural Network-Based Encryption Algorithm: Trends and Challenges

Abstract

Cloud computing has emerged as a critical platform for modern digital services because of its scalability, flexibility, cost efficiency, and ease of access. Despite these advantages, cloud environments face major security challenges related to data confidentiality, integrity, privacy, and secure information retrieval. Traditional encryption methods and conventional security protocols often struggle to handle large-scale distributed systems and increasingly sophisticated cyber threats. To overcome these limitations, researchers are integrating artificial intelligence, optimization algorithms, and quantum-inspired computing models into advanced cloud security frameworks. AI-based techniques, including deep learning and metaheuristic optimization, have demonstrated strong capabilities in detecting threats, optimizing resource allocation, and improving secure communication mechanisms. Among these approaches, the Giant Trevally Optimizer (GTO), inspired by the hunting behaviour of giant trevally fish, has gained attention for its efficient exploration and exploitation abilities in solving complex optimization problems related to cloud security and resource management. In addition, Quantum Convolutional Neural Networks (QCNNs) combine convolutional neural networks with quantum cryptographic principles to create highly secure encryption systems. QCNN-based encryption improves key randomness, strengthens resistance against cryptographic attacks, and enhances secure data storage and transmission, making hybrid AI-driven cloud security systems highly promising for future intelligent cloud infrastructures.