/* ---- Google Analytics Code Below */

Monday, November 06, 2017

Images Can be Constructed to Fool Deep Learning

A troublesome result,  especially where there is incentive to do so.

Fooling Neural Networks in the Physical World with 3D Adversarial Objects

We’ve developed an approach to generate 3D adversarial objects that reliably fool neural networks in the real world, no matter how the objects are looked at. ....  " 

More in MotherBoard.

No comments: