# Unrestricted Adversarial Challenge

This is a submission for the unrestricted adversarial challenge: Phase I. The
entry is uses a pretrained ImageNet model with Local Linearity Regularizer, then
adversarially trained using birds-or-bicycles dataset (train and extras) as
provided by the challenge.

> Tom B. Brown et al
  *Unrestricted Adversarial Examples*. [\[arXiv\]](https://arxiv.org/pdf/1809.08352).
> Chongli Qin et al
  *Adversarial Robustness through Local Linearization*. NEURIPS 2019. [\[arXiv\]](https://arxiv.org/abs/1907.02610)


## Contents

The code contains:

- a main file (`main.py`) for our submission.

## Running

Install requirements please follow instructions on
[Unrestricted Adversarial Challenge.](https://github.com/google/unrestricted-adversarial-examples/blob/master/warmup.md)

You can do this by running:

    ./unrestricted_advx/install_dependencies.sh

You can run the main script by:

    ./unrestricted_advx/run.sh