sis 18: e39

Research Article

Comparison of Classification Model for the Detection of Cyber-attack using Ensemble Learning Models

Download504 downloads
  • @ARTICLE{10.4108/eai.1-2-2022.173293,
        author={Muhammad Shoaib Akhtar and Tao Feng},
        title={Comparison of Classification Model for the Detection of Cyber-attack using Ensemble Learning Models},
        journal={EAI Endorsed Transactions on Scalable Information Systems: Online First},
        volume={},
        number={},
        publisher={EAI},
        journal_a={SIS},
        year={2022},
        month={2},
        keywords={cyberattack, machine learning, ensemble learning},
        doi={10.4108/eai.1-2-2022.173293}
    }
    
  • Muhammad Shoaib Akhtar
    Tao Feng
    Year: 2022
    Comparison of Classification Model for the Detection of Cyber-attack using Ensemble Learning Models
    SIS
    EAI
    DOI: 10.4108/eai.1-2-2022.173293
Muhammad Shoaib Akhtar1, Tao Feng1,*
  • 1: School of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, China
*Contact email: fengt@lut.com

Abstract

Incorporating digital technologies into security systems is a positive development. It's time for the digital system to be appropriately protected from potential threats and attacks. An intrusion detection system can identify both external and internal anomalies in the network. There are a variety of threats out there, both active and passive. If these dangers aren't addressed, attacks and data theft could occur from the point of origin all the way to the point of destination. Machine learning is still in its infancy, despite its wide range of applications. It is possible to predict the future by using machine learning. A cyber-attack detection system is depicted in this study using machine learning models. Machine learning algorithms were trained to predict cyber-attack scores using data from prior cyber-attacks on an open source website. In order to detect an attack at its earliest possible stage, this research also examined multiple linear machine learning algorithm-based categorization models. Classifiers' accuracy is also compared in the presentation, as is the presentation itself. Balance procedures were followed. Radio Frequency and GBC have the best accuracy, at 87.93%, followed by ABC at 86.11%, BT at 81.03%, ET at 70.31%, and DT at 70.31 percent (84.48 percent ).