Skip to main content

Table 3 Comparison overview of machine learning models with respect to DDoS detection

From: Detecting Denial of Service attacks using machine learning algorithms

ML model for detecting DDoS attacks Applications
Logistic Regression ▪ It is used to forecast the likelihood of a target variable using the supervised learning classification technique
Naive Bayes ▪ Predict a class of datasets for both binary and multi-class categorization
▪ In multi-class predictions, it performs better
C4.5 ▪Used to make a decision based on a sample of data either a univariate or multivariate predictors
KNN ▪ Evaluate the similarities between such a request and all the data items, select the K closest cases to the inquiry, and thereafter vote for the most common categorization
SVM ▪ Find a hyperplane in an N-dimensional space that categorises data points clearly
Fuzzy c-means ▪ Allows a single piece of data to belong to two or more clusters