Even Artificial Neural Networks Can Have Exploitable 'Backdoors'

  • Af
  • Episode
      123
  • Published
      31. aug. 2017
  • Forlag
0 Anmeldelser
0
Episode
123 of 2086
Længde
5M
Sprog
Engelsk
Format
Kategori
Fakta

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


Lyt når som helst, hvor som helst

Nyd den ubegrænsede adgang til tusindvis af spændende e- og lydbøger - helt gratis

  • Lyt og læs så meget du har lyst til
  • Opdag et kæmpe bibliotek fyldt med fortællinger
  • Eksklusive titler + Mofibo Originals
  • Opsig når som helst
Prøv nu
DK - Details page - Device banner - 894x1036

Other podcasts you might like ...