AI is everywhere and where it isn't today, it most likely will be tomorrow. But jumping on the hype train and adding AI often does not sufficiently consider security. This talk walks you through cases of AI failures, how they've come about, and how they could have been avoided. We're also going over some projections of spectacular AI failures we're likely to see going forward.

AI is ubiquitous. Where it isn't now, it will probably be soon, in software and operating systems. More often the usage guidelines are also unilaterally changed to companies utilising our data to train their models. While I've previously focused on building safer AI, now I also teach people how to hack them and build playgrounds for people to experiment. In this workshop I bring my hackable AI apps for people to play around with and hack so we may all learn new and necessary skills. Come play!