An Introduction to Adversarial Machine Learning (presented at Conference AI2019)

This is the repository for tutorial on Adversarial Machine Learning at The 32nd Australasian Joint Conference on Artificial Intelligence, 2-5 Dec 2019 Adelaide Australia

Presentors:

• Xingjun Ma (University of Melbourne)

• Sarah Erfani (University of Melbourne)

Slides: GoogleDrive

A step-by-step demo for crafting adversarial examples on MNIST: jupyter notebook

The crafted adversarial images (bottom) by the Fast Gradient Sign Method (FGSM) will look like this:

Prerequisites

• Python (3.6.4)
• Keras (2.2.4)
• numpy
• cleverhans (3.0.1)