EPISODE · Aug 31, 2017 · 5 MIN
Even Artificial Neural Networks Can Have Exploitable 'Backdoors'
from Security, Spoken · host WIRED
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
NOW PLAYING
Even Artificial Neural Networks Can Have Exploitable 'Backdoors'
No transcript for this episode yet
Similar Episodes
May 11, 2026 ·71m
May 4, 2026
Apr 27, 2026 ·51m
Apr 20, 2026 ·83m
Apr 13, 2026 ·84m
Apr 6, 2026 ·55m