Already purchased this program?
Login to View
This video program is a part of the Premium package:
Polarizing Front Ends For Robust Cnns
- IEEE MemberUS $11.00
- Society MemberUS $0.00
- IEEE Student MemberUS $11.00
- Non-IEEE MemberUS $15.00
Polarizing Front Ends For Robust Cnns
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
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