No description, website, or topics provided.
Branch: master
Clone or download
Sven Gowal
Latest commit 5fa09e7 Jan 23, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
examples Support for additional tensorflow operations. Jan 23, 2019
interval_bound_propagation Support for additional tensorflow operations. Jan 23, 2019
CONTRIBUTING.md Initial commit Dec 4, 2018
LICENSE
README.md Support for additional tensorflow operations. Jan 23, 2019
setup.py

README.md

On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models

This repository contains a simple implementation of Interval Bound Propagation (IBP) using TensorFlow: https://arxiv.org/abs/1810.12715

This is not an official Google product

Installation

IBP can be installed with the following command:

pip install git+https://github.com/deepmind/interval-bound-propagation`

IBP will work with both the CPU and GPU version of tensorflow and dm-sonnet, but to allow for that it does not list Tensorflow as a requirement, so you need to install Tensorflow and Sonnet separately if you haven't already done so.

Usage

This following command trains a small model on MNIST with epsilon set to 0.3:

cd examples
python train.py --model=small --output_dir=/tmp/small_model

Giving credit

If you use this code in your work, we ask that you cite this paper:

Sven Gowal, Krishnamurthy Dvijotham, Robert Stanforth, Rudy Bunel, Chongli Qin, Jonathan Uesato, Relja Arandjelovic, Timothy Mann, and Pushmeet Kohli. "On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models." arXiv preprint arXiv:1810.12715 (2018).