Hands on Adversarial Machine Learning

This project contains the Jupyter Notebooks and the associated Dockerfile for Yacin Nadji's Hands On Adversarial Machine Learning workshop/course. It contains both the exercises (/notebooks) and the solutions (/solutions), as well as any data or files needed (/data).

Running Jupyter Locally via Docker

The included Dockerfile will help you build an image for Jupyter, a fancy schmancy way of distributing interactive code.

You will need to have Docker installed on your system to create images and run containers. You can find the installation steps for all platforms on the company's website. If you're on OS X, you'll want to install Docker Desktop for Mac first. If you're on Linux, $ sudo apt-get|yum|whatever install docker|docker-ce is probably enough to get you going. I have not tested this with Windows, but I suspect installing Docker Desktop on Windows will work.

1. $ git clone https://github.com/ynadji/hands-on-adversarial-ml.git
2. $ cd hands-on-adversarial-ml
3. $ docker build -t advml .
4. $ docker run -p 8888:8888 advml
5. Open your browser to the Jupyter Notebook you just built.
6. Let's SMASH some models!