adversarial-classifier icon indicating copy to clipboard operation
adversarial-classifier copied to clipboard

It turns out that adversarial and clean data are not twins, not at all.

#+TITLE: Adversarial Classifier

This repo contains the code to reproduce the experiment in our paper (https://arxiv.org/abs/1704.04960), specifically the code to generate the figures and tables.

  • Code Dependencies :PROPERTIES: :CUSTOM_ID: sec:code-dependencies :END:
  1. Python 3.6+
  2. Keras https://keras.io/
  3. Tensorflow https://tensorflow.org
  4. tensorflow-adversarial https://github.com/gongzhitaao/tensorflow-adversarial
  • Datasets :PROPERTIES: :CUSTOM_ID: sec:datasets :END:

We used MNIST, CIFAR10 and SVHN in our experiment.

  • Document :PROPERTIES: :CUSTOM_ID: sec:document :END:

The paper itself is written in Org mode (http://orgmode.org/) employing the ICML2017 LaTeX template, with slight modification, i.e., removing the conference information.