After our introduction to adversarial examples and fooling AI in January, today we will dive deeper into how this actually works.
We'll focus on creating adversarial examples to trick image recognition algorithms, looking into the maths (30 mins) and then trying it out in practice (30 mins)!
To take part in the practical part of the workshop you will need to have Python, Tensorflow and Keras installed on your machine - please do this in advance as it takes a little time! Otherwise you can pair up with someone who already has their machine set up when you arrive.
Speaker is Dr. Abbey Wadron. Abbey has a PhD in experimental particle physics from the University of Oxford and has done research at many of the World's major laboratories including CERN, Fermilab and J-PARC.
17.30-17.45 – Meet & Greet
17.45-18.30 – Introduction to adversarial examples in AI
18.30-19.00 - Break with pizza