Upamanyu Madhow

Robust Adversarial Learning via Sparsifying Front Ends

2018 · arXiv (Cornell University)

It is by now well-known that small adversarial perturbations can induce classification errors in deep neural networks. In this paper, we take a bottom-up signal processing perspective to this problem and show that a systematic …

Polarizing Front Ends for Robust Cnns

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 …