Deep Learning and Optimization Approaches in Secure Cloud Data Storage and Retrieval Using Giant Trevally Optimizer with Quantum Convolutional Neural Network-Based Encryption Algorithm: A Review

Abstract

The rapid growth of cloud computing has significantly increased the demand for secure data storage and efficient retrieval mechanisms. However, cloud environments are highly vulnerable to data breaches, unauthorized access, and privacy leakage, necessitating advanced security solutions. Deep learning and optimization techniques have emerged as powerful tools for enhancing cloud security by enabling intelligent encryption, anomaly detection, and efficient data management. This paper presents a comprehensive review of deep learning and optimization approaches for secure cloud data storage and retrieval, focusing on the integration of the Giant Trevally Optimizer (GTO) with Quantum Convolutional Neural Network (QCNN)-based encryption algorithms. The GTO, a nature-inspired optimization technique, enhances feature selection and key generation processes, while QCNN-based encryption leverages quantum principles to provide robust data protection. Recent studies highlight the effectiveness of homomorphic encryption and deep learning models in enabling secure cloud-based inference without exposing raw data. Additionally, privacy-preserving deep learning frameworks demonstrate improved efficiency and scalability in cloud environment. The review analyses recent advancements, identifies key trends, and highlights challenges such as computational complexity, scalability, and quantum implementation constraints. Finally, future research directions for developing secure, efficient, and intelligent cloud storage systems are discussed.