DISTRIBUTED DENIAL OF SERVICE ATTACK DETECTION USING RANDOM FOREST ALGORITHM IN MACHINE LEARNING

Abstract

The Internet has changed the world in the
last few decades, but its growth has also brought
about many online dangers, most notably Distributed
Denial of Service (DDoS) attacks. These attacks stop
servers from working by flooding them with strange
traffic, which can slow them down or even cause the
system to crash. In today's digitally dependent world,
fighting this threat is very important. This project
uses advanced machine learning (ML) methods to
find DDoS attacks quickly, which are becoming a
bigger problem. Because DDoS attacks change all the
time, there isn't just one answer that works.
Classification methods like Decision Trees, Random
Forest, and KNN are used to tell the difference
between regular traffic and harmful behavior after a
lot of study. The main goal of the study is to create a
strong DDoS monitoring system that uses machine
learning techniques to look at trends in network data.
The system tries to quickly spot possible DDoS
attacks by learning from past data and tracking in real
time. To find DDoS attack trends in network data,
ensemble learning, especially the Random Forest
method, is used. By using various decision trees, this
method provides a strong defense against DDoS
threats.