Home → News → Even Artificial Neural Networks Can Have Exploitable... → Full Text

Even Artificial Neural Networks Can Have Exploitable 'backdoors'

By Wired

August 28, 2017

[article image]


Early in August, NYU professor Siddharth Garg checked for traffic, and put a yellow Post-it onto a stop sign outside the Brooklyn building in which he works.

From Wired
View Full Article

0 Comments

No entries found