Anomaly based intrusion detection uses statistics to form a baseline usage of the networks at different time intervals. This system uses machine learning to create a model simulating regular activity and then compares new behaviour with the existing model.
In this project, we have used KDD99 dataset to evaluate the performace of different machine learning models. All the code has been implemented in google colab. You can run and change the code by making a copy of the original colab sheet.
To clone the project in your local systems:
$ git clone https://github.com/piyush-palta/anomaly-detection-system.gitAll the code is available in colab sheet You need to run each cell for code execution. Follow the instructions in the notebook.
- Random Forest Classifier
- MLP (Multi-layered Perceptron)
- Deep Neural Network
- Logistic Regression
- KNN Classifier
- Decision Tree Classifier