Even Artificial Neural Networks Can Have Exploitable 'Backdoors'
Even Artificial Neural Networks Can Have Exploitable 'Backdoors'
Security, Spoken · SpokenLayer
August 31, 20175m 27s
Audio is streamed directly from the publisher (dovetail.prxu.org) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.
Show Notes
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.
Learn about your ad choices: dovetail.prx.org/ad-choices