Improved Adversarial Robustness by Reducing Open Space Risk via Tent Activations

Understand

Adversarial examples contain small perturbations that can remain imperceptible to human observers but alter the behavior of even the best performing deep learning models and yield incorrect outputs.

• Since their discovery, adversarial examples have drawn significant attention in machine learning: researchers try to reveal the reasons for their existence and improve the robustness of machine learning models to adversarial perturbations.
• The state-of-the-art defense is the computationally expensive and very time consuming adversarial training via projected gradient descent (PGD).
• We hypothesize that adversarial attacks exploit the open space risk of classic monotonic activation functions.