DDOS Attack Prediction using Deep Learning

Abstract

DDoS attacks on distributed networks are another name for distributed network attacks. These attacks exploit specific constraints that are applicable to every arrangement asset, like the authorized organization’s website framework. This proposes a deep learning approach for predicting DDoS attacks. Deep learning methods were developed for the purpose of classifying attacks. The deep learning method includes the classification methods Multilayer Perceptron and Long Short-Term Memory Grids. The datasets are pre-processed using StandardScaler. Distributed denial-of-service attack detection and categorization are aided by deep learning techniques. MLP is an artificial neural network feed-forward model that maps input sets to output sets. The LSTM classifier is designed to classify faults based on this proposed project produced a confusion matrix to identify the performance of the model, and it is used for fault diagnosis in that region. This implemented in Python software.