§ feed · storyline
Attacking machine learning with adversarial examples
OpenAI publishes an explainer on adversarial examples, showing how attackers craft inputs to deliberately mislead machine learning models across different mediums.
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 different mediums, and will discuss why securing systems against them can be difficult.
§ sources1 publication · timeline below