A Theoretical Framework for Robustness of (Deep) Classifiers against Adversarial Examples

Understand

Most machine learning classifiers, including deep neural networks, are vulnerable to adversarial examples.

• Such inputs are typically generated by adding small but purposeful modifications that lead to incorrect outputs while imperceptible to human eyes.
• The goal of this paper is not to introduce a single method, but to make theoretical steps towards fully understanding adversarial examples.
• By using concepts from topology, our theoretical analysis brings forth the key reasons why an adversarial example can fool a classifier ($f_1$) and adds its oracle ($f_2$, like human eyes) in such analysis.