作者
Matthew Mirman, Timon Gehr, Martin Vechev
发表日期
2018/7/3
研讨会论文
ICML 2018
简介
We introduce a scalable method for training robust neural networks based on abstract interpretation. We present several abstract transformers which balance efficiency with precision and show these can be used to train large neural networks that are certifiably robust to adversarial perturbations.
学术搜索中的文章
M Mirman, T Gehr, M Vechev - International Conference on Machine Learning, 2018