It’s disturbingly easy to trick AI into doing something deadly
https://www.vox.com/future-perfect/2019/4/8/18297410/ai-tesla-self-driving-cars-adversarial-machine-learning
How “adversarial attacks” can mess with self-driving cars, medicine, and the military.
Artificial intelligence researchers have a big problem. Even as they design powerful new technologies, hackers are figuring out how to trick the tech into doing things it was never meant to — with potentially deadly consequences.