DDos Attacks-Applications for Traffic Classification using ML Algorithms

Abstract

This project aims to develop a traffic classification system utilizing machine learning algorithms contributing to a more resilient digital environment. In the realm of cyber security DDos attacks continue to threaten online services. This project proposes a “Traffic Classification System Using Machine Learning Algorithms” as a defence against such attacks. The projects core objective is to build a system that can effectively distinguish between legitimate network Traffic and malicious DDos attack. Term effectiveness against evolving threats. Scale and perform efficiently even in large-scale networks, maintaining real-time detection capabilities. We analyse various ML methods and algorithms, conduct data analysis and model develop ment, and evaluate the effectiveness of the proposed approach. The results demonstrate that ML-based traffic classification and DDoS attack detection offers a powerful and practical solution for enhancing network security. Keywords: Traffic Classification, KNearest Neighbour, Logistic Regression, DDOS Attack