README.md

[1] Overview

This project was done in the subject, COMP90073 (Security Analytics) taken in Semester2, 2020 in the University of Melbourne.

• Detection of network traffic anomalies using unsupervised machine learning
• Anomaly_detection.ipynb: [2]~[5]
• Analysis.ipynb: [6] Interpretation of the result
• Generating_adversarial_samples.ipynb : [7] Generating Adversarial samples (FGSM), this notebook referred to this code (https://github.com/kenhktsui/adversarial_examples/blob/master/adversarial.py)
• Dataset link:

1. https://cloudstor.aarnet.edu.au/plus/s/Hvu7YyCDDG7ByWb
2. https://cloudstor.aarnet.edu.au/plus/s/38CH3I8HbuYkh3r

[2] Features

More details in the anomaly_detection_reports.pdf

• Feature1: Numeric value (existing + newly generated) + Standardscaler + PCA

• Feature2: Feature1 + One-hot encoded categorical feature

• Feature3: Scale (Cumulative features grouped by stream_id + time-based feature) + PCA

[3] Model

1. Iforest
2. OneclassSVM

[4] Hyperparameter tuning (2 examples among 6)

• Criteria of setting a threshold: Accuracy > 0.88 and Max(TPR-FPR)

1. OCSVM + feature3

2. Iforest + feature 3

[5] Clustering visualisation and Evaluation (2 examples among 6)

1. OCSVM + feature3

SCORES:

CLUSTERING:

2. Iforest + feature3

SCORES:

CLUSTERING:

[6] Interpretation of the result

• Attack Timeline

[7] Generating Adversarial samples (FGSM)

• FGSM generates adversarial samples with the error rate of almost 100%.