This is an official implementation of submitted ICCV2021 paper "Reg-IBP: Efficient and Scalable Neural Network Robustness Training via Interval Bound Propagation"
- Install pytorch
- Clone this repository
1.MNIST dataset 2.CIFAR10 dataset 3.TinyImageNet dataset 4.ShanghaiTech part A & B dataset
-
python3 tiny.py # Tiny imageNet challenge
-
python3 IBP_big_CIFAR_eps_8_255.py # CIFAR-10 challenge
-
python3 MNIST.py # reproduce the MNIST results
-
python3 soft_train.py # MCNN verifiably train
Baidu Disk: https://pan.baidu.com/s/1TZ8Ndqw6-6bG1bTihJP3ZA code: hary
trained models for MNIST and CIFAR10 datasets:
(Dropbox)
https://www.dropbox.com/sh/hn14wlkvg1m75k2/AABqXGC3PBjLTyU7lbQtHLDVa?dl=0