LeoMartinezTAMUK / Anomaly_Instrusion_Predictor

The following program is capable of analyzing network traffic with multiple different machine learning (ML) and feature selection algorithms to determine whether or not it is malicious.

Anomaly_Intrustion_Predictor

Author: Leo Martinez III

Contact: [e-mail]

Created: Spring 2023

The following program is capable of analyzing network traffic with multiple different machine learning (ML) algorithms to determine whether or not it is malicious. The user can enter what algorithm(s) they want to test and the output will be the results of its performance.

Dataset utilized: NSL-KDD

Program was created in Spyder 5.2.2 Anaconda with Python 3.9

***** Program is still under development and plans to be improved upon over time *****

Classification of network traffic using machine learning (ML) is important for several reasons, including:

Improved Security: One of the main reasons for using ML for network traffic classification is to improve security. By analyzing network traffic, ML algorithms can help identify and classify potentially malicious traffic, such as attacks, malware, and other threats. This can help security teams to quickly detect and respond to these threats, which can reduce the risk of cyber attacks and data breaches.

Automation: ML algorithms can automate the process of classifying network traffic, which can save time and resources for security teams. Instead of manually analyzing each network packet or log, ML algorithms can quickly and accurately analyze large volumes of data, which can help security teams to focus on high-priority threats and issues.

Scalability: As networks become more complex and the volume of network traffic increases, it becomes more difficult to manually classify network traffic. ML algorithms can scale to handle large volumes of data and can adapt to changes in network traffic patterns over time, which can help security teams to keep pace with the evolving threat landscape.

Accurate Classification: ML algorithms can learn from historical data and identify patterns and anomalies that may not be immediately obvious to human analysts. This can help to improve the accuracy of network traffic classification, reducing the risk of false positives and false negatives.

Overall, using ML for network traffic classification can help organizations to improve their security posture, automate the analysis of network traffic, scale to handle large volumes of data, and improve the accuracy of traffic classification.