Home BlogDataset Testing How Well AI Deals with Adversarial Examples

Testing How Well AI Deals with Adversarial Examples

by Joshua New
Adversarial examples

Researchers at UC Berkeley have published the Natural Adversarial Examples dataset, consisting of 7,500 images of natural phenomenon designed to fool image classification algorithms. Adversarial examples significantly reduce a classifier’s accuracy due to subtle visual elements that convince the algorithm it is seeing, for example, a manhole cover, rather than a dragonfly. Testing a classifier’s resilience to adversarial examples can help researchers overcome common flaws in classifier design, such as over-reliance on color or background cues. 

Get the data.

You may also like

Show Buttons
Hide Buttons