Fortified Networks: Improving the Robustness of Deep Networks by Modeling the Manifold of Hidden Representations
arXiv: Machine Learning, Volume abs/1804.02485, 2018.
Deep networks have achieved impressive results across a variety of important tasks. However a known weakness is a failure to perform well when evaluated on data which differ from the training distribution, even if these differences are very small, as is the case with adversarial examples. We propose Fortified Networks, a simple transforma...More