Performance Evaluation of Evolutionary Under Sampling and Machine Learning Techniques for Network Security in Cloud Environment

Despite the growing adoption of cloud computing, security challenges continue to persist in its implementation. In this study, we delve into the specific security challenges associated with cloud computing and explore the use of machine learning algorithms like K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree (DT), and Logistic Regression for anomaly detection. Our study leverages the MawiLab dataset to develop supervised machine learning models and evaluates their performance using key metrics such as accuracy, precision, recall, and F1-score. The results of our analysis showcase promising outcomes, with accuracy, precision, recall, and F1-score achieving impressive values of 96.3%, 93.8%, 95.2%, and 95.9% respectively. Nevertheless, the acquisition of real-time and unbiased datasets presents significant challenges. These findings underscore the importance of further research to enhance the applicability of machine learning techniques in effectively addressing the diverse operational conditions inherent in cloud environments.