ML Anthology

Differentiable Abstract Interpretation for Provably Robust Neural Networks

Matthew Mirman, Timon Gehr, Martin Vechev
ICML 2018 pp. 3578-3586
/icml/2018/mirman2018icml-differentiable/

Abstract

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.

PDF ICML Semantic Scholar

Cite

Text

Mirman et al. "Differentiable Abstract Interpretation for Provably Robust Neural Networks." International Conference on Machine Learning, 2018.

Markdown

[Mirman et al. "Differentiable Abstract Interpretation for Provably Robust Neural Networks." International Conference on Machine Learning, 2018.](https://mlanthology.org/icml/2018/mirman2018icml-differentiable/)

BibTeX

@inproceedings{mirman2018icml-differentiable,
  title     = {{Differentiable Abstract Interpretation for Provably Robust Neural Networks}},
  author    = {Mirman, Matthew and Gehr, Timon and Vechev, Martin},
  booktitle = {International Conference on Machine Learning},
  year      = {2018},
  pages     = {3578-3586},
  volume    = {80},
  url       = {https://mlanthology.org/icml/2018/mirman2018icml-differentiable/}
}