Random Forest Based Hypertext Transfer Protocol Distributed Denial of Service Attack Detection System for Cloud Computing Environment

Abstract

There is a need to secure data in the cloud from any form of attack. One among the many feared attacks in the cloud is the Hypertext Transfer Protocol Distributed Denial of Service (HTTP-DDoS) attack. HTTP-DDoS is the most devastating attack which stops the normal functionality of critical services provided by the various sectors in the cloud computing environment. Consequently, detection of HTTP-DDoS attack has attracted attention of many researchers, thereby leading to proposition of different approaches for detection of HTTP-DDoS attack in cloud computing environment. Meanwhile, machine learning approach is the most common approach previous researchers have used in addressing DDoS attack detection. However, achieving high detection accuracy with minimum false positive rate remains issue that still need to be addressed. Consequently, this study proposed solution to address the problem highlighted above by proposing machine learning based HTTP-DDoS attack detection system in cloud computing environment. To achieve this, the study designed a Random Forest based framework for HTTP-DDoS attack detection system. Thereafter, a Random Forest based model was formulated.The validation and testing of the model were carried out by experimentation with the application of data mining tool. Also, experimentation with other machine learning algorithms was carried out. Performance evaluation revealed that the Random Forest based model has an accuracy of 99.94% and minimum false positive rate of 0.001%. Also, when compared with existing detection models, this study detection model performed best in respect to accuracy and false positive rate.