Towards Stable and Efficient Training of Verifiably Robust Neural Networks
Boning, Duane S.
arXiv e-Print archive - 2019 via Local Bibsonomy
Zhang et al. combine interval bound propagation and CROWN, both approaches to obtain bounds on a network’s output, to efficiently train robust networks. Both interval bound propagation (IBP) and CROWN allow to bound a network’s output for a specific set of allowed perturbations around clean input examples. These bounds can be used for adversarial training. The motivation to combine BROWN and IBP stems from the fact that training using IBP bounds usually results in instabilities, while training with CROWN bounds usually leads to over-regularization.
Also find this summary at [davidstutz.de](https://davidstutz.de/category/reading/).