Enhancing Security of Data in Cloud Environment Using Convolutional Neural Network with SWO Optimizer

Data safety in cloud-based systems is crucial due to the increasing amount of sensitive data being handled and stored online. To ensure the security and integrity of cloud-based systems, robust defenses against data breaches and cyberattacks are necessary. This study offers a new approach to the hunt for state-of-the-art data security solutions for cloud settings by using a Hybrid Quantum-Classical Convolutional Neural Network with Spider Wasp Optimizer (HQCCNN-SWO). This method increases the accuracy and efficacy of data security detection by using state-of-the-art techniques. NSL-KDD, KDDCUP99, and UNSW-NB15 are three popular datasets that are used to train and evaluate the model in order to guarantee that it covers a broad variety of attack scenarios. The approach begins with global-local depth normalization-based preprocessing to normalize data and increase the robustness of feature extraction. By doing this, consistency is increased and differences in input distributions are addressed. A geometric algebra transformer is then used to extract features, improving feature representation by spotting intricate patterns and correlations in the data. The core component of the model, HQCCNN-SWO, blends quantum-classical convolutional neural network architecture, using the best characteristics of both conventional and quantum computers. By fine-tuning network parameters, the Spider Wasp Optimizer (SWO) maximizes performance via its advanced search capabilities and adaptive mechanisms. A powerful MATLAB framework called HQCCNN-SWO may be used to more precisely and efficiently identify security issues. This technique offers a robust and efficient tool for cloud environments, representing a substantial advancement in the detection of data security. Due to its combination of quantum-classical approaches and powerful optimization techniques, HQCCNN-SWO is a high-performing solution in the realm of cloud data security.