Research

Robust adversarial inputs

Source: OpenAI News 17 Jul 2017

Listen to Brief

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

Brief

We’ve created images that reliably fool neural network classifiers when viewed from varied scales and perspectives. This challenges a claim from last week that self-driving cars would be hard to trick maliciously since they capture images from multiple scales, angles, perspectives, and the like.

Why It Matters

Implikasinya penting untuk keselamatan kenderaan automatik dan reka bentuk model yang lebih tahan terhadap serangan.

Keep Reading on NadiAI

Selected Related Articles