Boosting Robustness Certification of Neural Networks
Gagandeep Singh ⋅ Timon Gehr ⋅ Markus Püschel ⋅ Martin Vechev
Keywords:
adversarial attacks
robustness certification
abstract interpretation
milp solvers
verification of neural networks
2019 Poster
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.
Chat is not available.
Successful Page Load