A HYBRID MACHINE LEARNING FRAMEWORK FOR SECURE DATA TRANSMISSION IN CLOUD COMPUTING
DOI:
https://doi.org/10.5281/zenodo.21990403Abstract
Cloud computing has become a fundamental technology for delivering scalable, flexible, and cost-effective computing services across various application domains. However, the increasing volume of data transmitted through cloud environments has introduced significant security challenges, including unauthorized access, data breaches, distributed denial-of-service (DDoS) attacks, and network intrusions. Traditional security mechanisms such as encryption, firewalls, and signature-based intrusion detection systems are often inadequate for detecting sophisticated and evolving cyber threats in real time. To address these challenges, this research proposes a Hybrid Machine Learning Framework for Secure Data Transmission in Cloud Computing that combines multiple machine learning techniques to improve intrusion detection accuracy while reducing computational complexity. The proposed framework utilizes the NSL-KDD benchmark dataset, where network traffic data undergoes preprocessing through data cleaning, label encoding, feature normalization, and feature optimization. An Artificial Bee Colony (ABC) optimization algorithm is employed to identify the most relevant features and optimize the parameters of an Artificial Neural Network (ANN), while K-Nearest Neighbour (KNN) serves as a baseline classifier for comparative evaluation. The performance of the proposed hybrid framework is assessed using standard evaluation metrics, including accuracy, precision, recall, F1-score, and confusion matrix analysis. Experimental results demonstrate that the hybrid ABC-ANN model outperforms conventional machine learning approaches by achieving higher detection accuracy, minimizing false-positive and false-negative rates, and improving computational efficiency. Furthermore, the optimized model is deployed through a Flask-based web application, enabling real-time intrusion detection and secure cloud data transmission. The proposed framework provides an intelligent, scalable, and reliable solution for enhancing cloud security and protecting cloud-based communication against evolving cyber threats.
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.













