A SUPERVISED MACHINE LEARNING MODEL FOR DETECTING NETWORK ATTACKS
Author(s):
Kenosi S. Mhlanga, Fungai Mukoko
Keywords:
Cloud computing, cloud security, supervised machine learning, classification algorithm, network, network attack.
Abstract
This study developed a supervised machine learning model to enhance security in cloud computing. An in-depth examination of the present cloud computing security architecture was conducted to better understand cloud security issues. The model used labelled data to detect and classify traffic as either normal or anomaly. The model developed performed better than the traditional techniques of traffic attack detection based on historical data of previously detected attacks to explore and learn the patterns of attacks such that the model can predict and classify traffic as an attack or not. The study developed and implemented five supervised machine learning models: Logistic regression, Naïve Bayes, XGBoost Classifier, LightGBM model, and the Support vector machine classifier. The target feature was the classified traffic class which is either ‘normal’ or ‘anomaly’. The two classes were encoded during feature engineering to produce two numerical traffic class codes: ‘ 0’ for normal traffic and ‘1’ for anomaly traffic. Coding was done using one-hot encoding. The results showed that the XGBoost Classifier model performs better than the other models as evaluated using four performance metrics namely, precision, f1 score, recall score and accuracy. The XGBoost scored the highest with a score of 100% on each metric and a reasonably low false positive of 15 entries. The study, therefore, concludes that the XGBoost classifier model is the best model to use in-network attack detection.
Article Details
Unique Paper ID: 154046

Publication Volume & Issue: Volume 8, Issue 9

Page(s): 552 - 559
Article Preview & Download


Share This Article

Conference Alert

NCSST-2021

AICTE Sponsored National Conference on Smart Systems and Technologies

Last Date: 25th November 2021

SWEC- Management

LATEST INNOVATION’S AND FUTURE TRENDS IN MANAGEMENT

Last Date: 7th November 2021

Go To Issue



Call For Paper

Volume 8 Issue 4

Last Date 25 September 2021

About Us

IJIRT.org enables door in research by providing high quality research articles in open access market.

Send us any query related to your research on editor@ijirt.org

Social Media

Google Verified Reviews

Contact Details

Telephone:6351679790
Email: editor@ijirt.org
Website: ijirt.org

Policies