1. Home
  2. Premium
  3. IEEE ICASSP 2020 Virtual Conference May 2020
  4. Polarizing Front Ends For Robust Cnns

Polarizing Front Ends For Robust Cnns

Collection:
IEEE ICASSP 2020 Virtual Conference May 2020
The vulnerability of deep neural networks to small, adversarially designed perturbations can be attributed to their ?excessive linearity.? In this paper, we propose a bottom-up strategy for attenuating adversarial perturbations using a nonlinear front end
  • IEEE MemberUS $11.00
  • Society MemberUS $0.00
  • IEEE Student MemberUS $11.00
  • Non-IEEE MemberUS $15.00
Purchase

Videos in this product

Polarizing Front Ends For Robust Cnns

00:14:49
0 views
The vulnerability of deep neural networks to small, adversarially designed perturbations can be attributed to their ?excessive linearity.? In this paper, we propose a bottom-up strategy for attenuating adversarial perturbations using a nonlinear front end