728x90
Paper
Adversarial Examples Are Not Bugs, They Are Features
Adversarial examples have attracted significant attention in machine learning, but the reasons for their existence and pervasiveness remain unclear. We demonstrate that adversarial examples can be directly attributed to the presence of non-robust features:
arxiv.org
Introduction
그동안 adversarial example에 대한 여러가지 해석이 있었다.
본 논문에서는 사실 adversarial example은 deep learning model이 학습하는 featrue는
robust-feature와 non-robust feature 2가지로 나뉘게 되며,
adversarial example은 non-robust feature를 이용한 것이란 것을 증명한다.
728x90