urihsam / AIN

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Adversarial Transformation Network(ATN)

Introduction

A simple implement of an Adversarial Autoencoding ATN(AAE ATN) proposed in Adversarial Transformation Networks: Learning to Generate Adversarial Examples using tensorflow.

Requirements

python 3.5

tensorflow 1.1.0

matplotlib (for result visualizing)

Usage

You can test with my trained model:

python atn.py

If you want to train by yourself:

python atn.py --train

Result

Here are some visualized samples:

result

Before attack, the accuracy of the target cnn network is 0.9902, and it becomes 0.2773 after attack.

The result is not good enough, so WELCOME CONTRIBUTION !!!

About


Languages

Language:Python 99.2%Language:Shell 0.8%