Skip to content

This project focuses on implementing anomaly detection in computer networks using TensorFlow to develop AI models that efficiently identify abnormal network patterns and enhance real-time security.

License

Notifications You must be signed in to change notification settings

AreejFatimaz/Network-Traffic-Analysis-using-Machine-Learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Network-Traffic-Analysis-using-Machine-Learning

In the rapidly evolving field of cybersecurity, anomaly detection has become essential for protecting computer networks from malicious activities and irregular behavior. This technique identifies deviations from established patterns of normal network activity, helping to detect security threats or network malfunctions in real-time. By using AI and machine learning, anomaly detection systems can analyze historical data to define "normal" behavior and spot irregularities that indicate potential intrusions or vulnerabilities.

TensorFlow can be leveraged to optimize anomaly detection models, offering high efficiency without the need for external hardware acceleration like Intel’s extensions. This enables the processing of large datasets swiftly, crucial for high-traffic networks, making systems more adaptive and reliable in identifying security threats.

In the pursuit of robust anomaly detection in computer network data, a combination of two powerful techniques has been employed: Isolation Forest and Autoencoders. This dual approach harnesses the strengths of both methodologies to enhance the precision and effectiveness of anomaly detection in complex network environments.

About

This project focuses on implementing anomaly detection in computer networks using TensorFlow to develop AI models that efficiently identify abnormal network patterns and enhance real-time security.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published