Exploring Robust DDoS Detection: A Machine Learning Analysis with the CICDDoS2019 Dataset
Kamal Saluja, Susama Bagchi, Vikas Solanki, Muhammad Numan Khan, Esha Dhamija, Sanjoy Kumar Debnath · 2024
The ever-present threat posed by Distributed Denial of Service attack is highlighted. The significance of building robust cybersecurity measures that are not just inventive but also flexible. The purpose of this study paper is to investigate the effectiveness of an algorithm based on machine learning in detecting distributed denial of service assault to strengthen the resilience of Internet infrastructure. Random forest, decision tree, naïve bayes, and KNN are some of the machine learning techniques that are investigated in this study. The dataset used for this investigation is the CICDDoS 2019 data, Moreover, the research broadened its approach to identify the role of Artificial Intelligence in the Cybersecurity Framework. It does this by providing insight into the relative merits of various algorithms. The study, in its essence, highlights the critical role that adaptive and intelligent defense systems play in decreasing the impact of distributed denial of service assaults (DDoS). This provides a foundation for prepared strategies in the constantly shifting world of cybersecurity.