Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network
international conference on learning representations, 2019.
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
PPT (Upload PPT)