Detection of Distributed Denial of Service (DDoS) Attacks Using Computational Intelligence and Majority Vote-Based Ensemble Approach

Detection of Distributed Denial of Service (DDoS) Attacks Using Computational Intelligence and Majority Vote-Based Ensemble Approach

Anupama Mishra, Bineet Kumar Joshi, Varsha Arya, Avadhesh Kumar Gupta, Kwok Tai Chui
DOI: 10.4018/IJSSCI.309707
(Individual Articles)
No Current Special Offers


The term “distributed denial of service” (DDoS) refers to one of the most common types of attacks. Sending a huge volume of data packets to the server machine is the target of a DDoS attack. This results in the majority of the consumption of network bandwidth and server, which ultimately leads to an issue with denial of service. In this paper, a majority vote-based ensemble of classifiers is utilized in the Sever technique, which results in improved accuracy and reduced computational overhead, when detecting attacks. For the experiment, the authors have used the CICDDOS2019 dataset. According to the findings of the experiment, a high level of accuracy of 99.98% was attained. In this paper, the classifiers use random forest, decision tree, and naïve bayes for majority voting classifiers, and from the results and performance, it can be seen that majority vote classifiers performed better.
Article Preview


In today`s era, the latesest technology enables the sharing of multiple resources like storage, or may be network bandwidth, and/or computational cpabilities Aamir, M., & Zaidi, S. M. A. (2019). The authors Alzahrani, R. J., & Alzahrani, A. (2021) said that it gives both the business and individual users the ability to use resources as per their demands like cloud computing. In addition to details on the safety precautions that have been taken, the SLA document provides exhaustive information on the services that have been rendered. Users who save their data in the cloud express significant apprehension and worry about the cloud's potential to compromise the confidentiality of their information. Even while cloud servers are protected from intrusions by security measures, there are still instances in which an assault could be carried out undetected. The static security model employed by on-premises software applications is undermined by the dynamic nature of cloud platforms. Invasive cancer is the biggest cause of death worldwide, especially among women. Early cancer detection is vital to health. Early identification of breast cancer improves prognosis and survival odds by allowing for timely clinical therapy. For accurate cancer prediction, machine learning requires quick analytics and feature extraction. Cloud-based machine learning Chartuni, A., & Márquez, J. (2021) and Chelliah, P. R., & Surianarayanan, C. (2021) is vital for illness diagnosis in rural areas with few medical facilities

The majority of attacks Chopra, M. et al. (2022) that have been documented in cloud computing have been DDOS attacks, which aim to bring down a cloud's underlying network infrastructure.

DDOS attacks are executed by compromising and exploiting a huge number of hosts Cvitić, al. (2021) and Dahiya, A., & Gupta, B. B. (2021) which are referred to as zombies, in order to launch an attack against the system that is being targeted. They do this by causing an abrupt exponential surge in traffic, which clogs up the network capacity and, as a result, prevents regular data from reaching its destination. This disrupts the normal flow of traffic on the network. Extortion has been acknowledged as one of the primary motivating elements behind this attack, which have begun to increase in scale and sophistication. As per author Dahiya, A., & Gupta, B. B. (2020) A Distributed Denial of Service (DDOS) assault is a type of malicious attack against cloud systems that can create significant disruptions.

The authors Gupta, B. B., & Badve, O. P. (2017) said that the existing solutions for protecting against distributed denial of service (DDOS) attacks need a data packet to be categorised as either legitimate or malicious Guebli, W., & Belkhir, A. (2021). These techniques can be broken down into two primary groups: those that are signature-based and those that are anomaly-based. Utilizing previously crafted attack signatures that have been saved in a database is one of the steps involved in the signature-based detection technique Gupta, B. B. et al. (2020). Using a method of detection that is based on signatures has one major drawback, which is that it is unable to locate new malware variants until the signatures of those variants are updated in the database. Gupta, B. B. et al. (2021) cybercriminals have the ability to avoid detection by using the amount of time that has passed since a new attack was launched and then updating the definitions that are stored in the database Gupta, B. B. et al. (2015) and Gupta, B. B. et al. (2022).

Complete Article List

Search this Journal:
Volume 16: 1 Issue (2024)
Volume 15: 1 Issue (2023)
Volume 14: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 13: 4 Issues (2021)
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing