It's recommended to open Jupyter notebooks in Google Colabоratory.

https://colab.research.google.com/github/fisher85/ml-cybersecurity/blob/master/ai-index-report-2019-research/cybersecurity_startups.ipynb

https://colab.research.google.com/github/fisher85/ml-cybersecurity/blob/master/python-logistic-regression-fraud-detection/python-logistic-regression-fraud-detection.ipynb

https://colab.research.google.com/github/fisher85/ml-cybersecurity/blob/master/python-waf/machine-learning-waf.ipynb

Classifier comparison: https://colab.research.google.com/github/fisher85/ml-cybersecurity/blob/master/python-web-attack-detection/classifier-comparison.ipynb

Web attack detection: https://colab.research.google.com/github/fisher85/ml-cybersecurity/blob/master/python-web-attack-detection/web-attack-detection.ipynb

Web attack detection using CNN-BiLSTM: https://colab.research.google.com/github/fisher85/ml-cybersecurity/blob/master/python-web-attack-detection/web-attack-detection-using-CNN-BiLSTM.ipynb

Defending ML IDS against an evasion attack using adversarial training: https://colab.research.google.com/github/fisher85/ml-cybersecurity/blob/master/adversarial-attacks/evasion-attack.ipynb

Comparison of adversarial attacks: https://colab.research.google.com/github/fisher85/ml-cybersecurity/blob/master/adversarial-attacks/comparison_of_adversarial_attacks.ipynb

Iterative adversarial training with the HSJA attack and a Random Forest model using CICIDS2017 dataset: https://colab.research.google.com/github/fisher85/ml-cybersecurity/blob/master/adversarial-attacks/iterative_adversarial_training_with_HSJA.ipynb