Quantcast
Channel: Anish Athalye
Viewing all articles
Browse latest Browse all 79

Robust Adversarial Examples

$
0
0

I recently wrote a post on the OpenAI blog about how we created images that reliably fool neural network classifiers when viewed from various scales and perspectives, challenging a recent claim that adversarial examples aren’t an issue for self-driving cars because cars see images from multiple scales and angles.

The video above shows that our adversarial kitten photo, printed on a standard color printer, fools the classifier into thinking it’s a “desktop computer” regardless of how it’s zoomed or rotated.

Read the full story about how we did it on the OpenAI blog.


Viewing all articles
Browse latest Browse all 79

Trending Articles