The Gap Between Research And Robust AI

Table of Contents

1. What is this repo about?
2. Blog post
3. Notebook
4. Let's connect!

What is this repo about?

Would you say Deep Learning models have become so good, that robust AI systems are no longer a dream, but a reality?

Do you think you can safely use the latest models published by researchers in any real-world problem, like self-driving cars? Or face recognition software at airports?

Convinced that machines are already better than humans at processing and understanding images?

I was too. Until I realized it is possible to deceive a state-of-the-art model, like DeepMind Perceiver, with a few lines of code

In this repo, I show you how.

Blog post

📝 The Gap Between Research And Robust AI

Notebook

You can run this tutorial on your local computer or directly on Colab.

To run locally

Create a virtual environment for Python >= 3.8, and activate it:

$ (venv) git clone https://github.com/Paulescu/fooling_deepmind.git
$ (venv) pip install jupyter
$ (venv) jupyter notebook

Then open the notebook

To run on Google Colab

Click on this button

Let's connect

If you want to learn more about real-world ML topics and become a better data scientist

👉 Subscribe to the datamachines newsletter.

👉🏽 Follow me on Twitter and/or LinkedIn