Research

Attacking machine learning with adversarial examples

Source: OpenAI News 24 Feb 2017

Listen to Brief

AI audio in English, based on the NadiAI brief and original source.

Brief

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.

Why It Matters

Memahami ancaman ini penting untuk membangunkan pembelaan yang kukuh terhadap kesilapan model dan risiko keselamatan.

Keep Reading on NadiAI

Selected Related Articles