We’ve touched previously on the concept of adversarial examples—the class of tiny changes that, when fed into a deep-learning model, cause it to misbehave. More...
9 juin 2019
How we might protect ourselves from malicious AI
Commentaires
We’ve touched previously on the concept of adversarial examples—the class of tiny changes that, when fed into a deep-learning model, cause it to misbehave. More...