Projects / Computer Science / Computer Science project 22

Machine Learning Based Network Intrusion Detection System

Approx. component budget: Rs. 0 - 1,000

Objective

Train and compare detectors on a public intrusion dataset and study the false alarm rate.

What you will build

A model that classifies network traffic records as normal or as an attack type such as DoS, probe or brute force, with a live dashboard on recorded traffic.

Results you can expect

• Accuracy
• Recall for each attack class
• False positive rate
• Comparison of Random Forest
• XGBoost and a neural network
• And a test on a different dataset to check generalisation

What you will learn

Network features, imbalanced classes, why accuracy alone is misleading in security, and dataset limits.

Tools and notes

Python, scikit-learn, NSL-KDD or CIC-IDS2017 dataset, Streamlit or Grafana. Mention that the datasets are old and may not match modern traffic.

Resume points from this project

• Built and tested Machine Learning Based Network Intrusion Detection System; objective: train and compare detectors on a public intrusion dataset and study the false alarm rate.
• Measured and analysed accuracy and recall for each attack class; wrote the report and presented the results in a viva. Add your own numbers: [x].

Replace [x] with your own measured results. Write only what you really did.

More computer science projects

Back to all projects