Boosting Robustness Certification of Neural Networks

Abstract

We present a novel approach for the certification of neural networks against adversarial perturbations which combines scalable overapproximation methods with precise (mixed integer) linear programming. This results in significantly better precision than state-of-the-art verifiers on challenging feedforward and convolutional neural networks with piecewise linear activation functions.

Cite

Text

Singh et al. "Boosting Robustness Certification of Neural Networks." International Conference on Learning Representations, 2019.

Markdown

[Singh et al. "Boosting Robustness Certification of Neural Networks." International Conference on Learning Representations, 2019.](https://mlanthology.org/iclr/2019/singh2019iclr-boosting/)

BibTeX

@inproceedings{singh2019iclr-boosting,
  title     = {{Boosting Robustness Certification of Neural Networks}},
  author    = {Singh, Gagandeep and Gehr, Timon and Püschel, Markus and Vechev, Martin},
  booktitle = {International Conference on Learning Representations},
  year      = {2019},
  url       = {https://mlanthology.org/iclr/2019/singh2019iclr-boosting/}
}