Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network

international conference on learning representations, 2019.

Cited by: 31|Bibtex|Views26|Links
EI

Abstract:

We present a new algorithm to train a robust neural network against adversarial attacks. Our algorithm is motivated by the following two ideas. First, although recent work has demonstrated that fusing randomness can improve the robustness of neural networks (Liu 2017), we noticed that adding noise blindly to all the layers is not the opti...More

Code:

Data:

Your rating :
0

 

Tags
Comments