Cloud computing is advancing technology that provides scalability and accessibility to everyone at low prices. Similarly, everyone can access and use the cloud data from anywhere. This widespread service accessibility leads to security issues. In the digital landscape, distributed denials of service (DDoS) attacks are the most prevalent security threat. These attacks aim to disrupt the service availability of a target system or network with a flood of traffic, rendering it inaccessible to legitimate users. The proposed work leverages a virtual machine-based cloud environment to defend against DDoS attacks. The proposed work objective is to detect DDoS attacks swiftly and accurately to mitigate their impact. To achieve this goal, the machine learning algorithms such as Naive Bayes (NB), K-Nearest Neighbours (KNN), random forest (RF) and decision tree (DT) algorithms have been used in the proposed work to analyze the large number of application-layer packets. To detect the DDoS attacks, the proposed work is implemented in Wireshark for analyzing incoming packets. Compared to NB, KNN and DT models, the RF model achieved a comprehensive and highest detection accuracy rate of 99.3%.