Podcasts Technology Security, Spoken Even Artificial Neural Networks Can Have Exploitable 'Backdoors'

Even Artificial Neural Networks Can Have Exploitable 'Backdoors'

Published: Aug. 31, 2017, 8:59 a.m.

b'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. 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. The stunt demonstrated a potential security headache for engineers working with machine learning software.\\nLearn more about your ad choices. Visit podcastchoices.com/adchoices'