Training Robust Deep Neural Networks via Adversarial Noise Propagation

Understand

In practice, deep neural networks have been found to be vulnerable to various types of noise, such as adversarial examples and corruption.

• Various adversarial defense methods have accordingly been developed to improve adversarial robustness for deep models.
• However, simply training on data mixed with adversarial examples, most of these models still fail to defend against the generalized types of noise.
• Motivated by the fact that hidden layers play a highly important role in maintaining a robust model, this paper proposes a simple yet powerful training algorithm, named \emph{Adversarial Noise Propagation} (ANP), which injects noise into the hidden layers in a layer-wise manner.