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.
Related Posts
Robust adversarial inputs
We’ve created images that reliably fool neural network classifiers when viewed from varied scales and perspectives. This challenges a claim…
Hoax: Fake Russian “troll” error message
OpenAI banned an account that likely originated in the US and used AI to create a fake ChatGPT error message…
GPT-6 Astra: The next generation in intelligence for work
Meet GPT-6 Astra, OpenAI’s most capable model for business, with advanced reasoning, computer use, and stronger writing and design judgment.
