Abstract :

Cloud Computing Has Emerged As A Costeffective And Scalable Solution For Deploying Modern Applications By Offering High Computational Power And Storage Capabilities. However, Its Reliance On Network Connectivity Exposes It To Various Cyber Threats Such As Distributed Denial Of Service (DDoS) And Man-in-the-Middle (MITM) Attacks, Which Compromise Data Transmission Security. Traditional Cryptographic Techniques, While Effective, Often Involve High Computational Overhead And Remain Vulnerable If Encryption Keys Are Compromised. To Address These Limitations, This Work Proposes A Machine Learning-based Framework For Enhancing Data Transmission Security In Cloud Environments. The System Utilizes K-Nearest Neighbors (KNN) And Artificial Neural Networks (ANN) For Anomaly Detection, With Further Performance Enhancement Achieved Through The Integration Of The Artificial Bee Colony (ABC) Optimization Algorithm. The ABC Algorithm Optimizes ANN By Selecting The Best Feature Subset And Tuning Hyperparameters Such As Learning Rate, Number Of Neurons, And Epochs, Inspired By The Foraging Behavior Of Honeybees. The Model Is Trained And Evaluated Using The NSL-KDD Dataset, Which Consists Of 41 Features Related To Network Traffic. After Preprocessing And Feature Optimization, 32 Significant Features Were Selected. Experimental Results Demonstrate That KNN Achieved 96% Accuracy, ANN Achieved 97%, While The Optimized ANN-ABC Model Achieved A Superior Accuracy Of 99%, Along With Improved Precision, Recall, And F1-score. The Implementation Is Carried Out Using Jupyter Notebook For Model Training And Flask Framework For Real-time Prediction Through A Web Interface. The Results Confirm That The Proposed ANN-ABC Model Significantly Enhances Intrusion Detection Performance, Making It A Reliable Solution For Securing Cloud Data Transmission.

Published:

08-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

1992-1999

Section:

Articles

License:

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

How to Cite