Attacking Machine Learning with Adversarial Examples

Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to cause the model to make a mistake; they’re like optical illusions for machines. In this post we’ll show how adversarial examples work across differen… Read more


Stealing Machine Learning Models via Prediction APIs

Imagine our world later in this century, when machines have gotten better. Cars and trucks drive themselves, and there’s hardly ever an accident.  Robots root through the earth for raw materials, and miners are never trapped. Robotic surgeons rarely ...

Read more »