This report delves into the application of data analytics for intrusion detection within network security. It begins with an overview of Big Data and its relevance, exploring data analytics tools such as SAS Visual Analytics, Sisense, and Weka. The report details the use of the UNSW-NB15 dataset and employs data analytics techniques like clustering, decision trees (J48), and back-propagation algorithms (MLP) to analyze network traffic. Weka, Wireshark, and IXIA are used to analyze normal and abnormal traffic. Different data formats like CSV, Bro, and Cap are examined alongside testing data samples from NSL-KDD. Support Vector Machine (SVM) and Random Forest classifiers are employed, with feature selection using RFE. The report presents results using confusion matrices to evaluate the performance of the algorithms for detecting various types of attacks. Finally, it discusses the limitations of the methods and suggests recommendations for future work, emphasizing the importance of Big Data analytics for real-time security insights and improved decision-making.
![[object Object]](/_next/static/media/star-bottom.7253800d.svg)
