Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach

Understand

The robustness of neural networks to adversarial examples has received great attention due to security implications.

• Despite various attack approaches to crafting visually imperceptible adversarial examples, little has been developed towards a comprehensive measure of robustness.
• In this paper, we provide a theoretical justification for converting robustness analysis into a local Lipschitz constant estimation problem, and propose to use the Extreme Value Theory for efficient evaluation.
• Our analysis yields a novel robustness metric called CLEVER, which is short for Cross Lipschitz Extreme Value for nEtwork Robustness.