The Denial of Service (DoS) attack is a type of attack by which an online service is overwhelmed with network traffic, preventing the system from providing service to legitimate users. This attack's main goal is to disrupt an online service's efficiency. One variant of the DoS attack is called the Distributed Denial of Service (DDoS). The key difference between the two is that a DDoS attack comes from multiple sources. Machine Learning is a subset of Artificial Intelligence that allows machines to learn without explicit programming. Research has shown that Machine Learning (ML) can be a useful tool to defend against DoS and DDoS attacks. ML is trained to detect malicious networks using massive sets of data called datasets. It has the ability to constantly learn and improve from new data it processes. This feature makes it a good tool for attack detection. Ten Machine Learning algorithms were analyzed to reveal which was more efficient in defending against DoS and DDoS attacks. The algorithms were analyzed on the basis of accuracy, F1 score, and recall. The algorithms tested were XGBoost, AdaBoost, Naive Bayes (NB), Decision Tree (DT), Convolutional Neural Network (CNN), K Nearest Neighbor (KNN), Random Forest (RF), Deep FeedForward (DFF), Factorisation Machine algorithm (FM), and Generative Adversarial Network (GAN). The algorithm with the best performance across all evaluation metrics was Decision Tree. It produced an accuracy of 99.93%, an F1 score of 100%, and a recall of 100%.