This document outlines a machine learning project on network intrusion detection. It presents the objectives, which are to detect network intrusions using supervised machine learning algorithms like Naive Bayes, Decision Tree, K-Neighbors and Logistic Regression. The best performing model was found to be Decision Tree classification, which achieved 99.60% accuracy on the test data. The document discusses the system model, problem statement, data collection and preprocessing steps, model training and evaluation, and concludes with possibilities for future work such as using different datasets and deep learning approaches.