ATRO: Adversarial Training with a Rejection Option

Understand

This paper proposes a classification framework with a rejection option to mitigate the performance deterioration caused by adversarial examples.

• While recent machine learning algorithms achieve high prediction performance, they are empirically vulnerable to adversarial examples, which are slightly perturbed data samples that are wrongly classified.
• In real-world applications, adversarial attacks using such adversarial examples could cause serious problems.
• To this end, various methods are proposed to obtain a classifier that is robust against adversarial examples.