Sunday, April 16, 2017

Fooling Deep Neural Networks

Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
http://www.evolvingai.org/fooling

Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition
https://www.cs.cmu.edu/~sbhagava/papers/face-rec-ccs16.pdf

Magic AI: these are the optical illusions that trick, fool, and flummox computers
http://www.theverge.com/2017/4/12/15271874/ai-adversarial-images-fooling-attacks-artificial-intelligence 

No comments:

Post a Comment