How to hide backdoor in AI software
Early in August, NYU professor Siddharth Garg checked for traffic, and then put a yellow Post-it onto a stop sign outside the Brooklyn building in which he works. When he and two colleagues showed a photo of the scene to their road-sign detector software, it was 95 percent sure the stop sign in fact displayed a speed limit.
Machine Learning, Artificial Intelligence, and Deep Learning News around the world. We publish the latest developments and advances in these fields.
Saturday, August 26, 2017
Even Artificial Neural Networks Can Have Exploitable 'Backdoors'
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment