Towards Stable and Efficient Training of Verifiably Robust Neural Networks

ICLR, 2020.

Cited by: 0|Bibtex|Views79|Links
EI

Abstract:

Training neural networks with verifiable robustness guarantees is challenging. Several existing approaches utilize linear relaxation based neural network output bounds under perturbation, but they can slow down training by a factor of hundreds depending on the underlying network architectures. Meanwhile, interval bound propagation (IBP) b...More

Code:

Data:

Your rating :
0

 

Tags
Comments