The approach
You've decided to take a four-fold approach, as follows:
- Exploring several possible evasion attacks to understand how vulnerable the model is to them and how credible they are as threats
- Using a preprocessing method to protect the model against these attacks
- Leveraging adversarial retraining to produce a robust classifier that is intrinsically less prone to many of these attacks
- Evaluating robustness with state-of-the-art methods to be able to assure hospital administrators that the model is adversarially robust
Let's get started!
