# Polarizing Front Ends for Robust CNNs

arXiv: https://arxiv.org/abs/2002.09580 · HTML: https://mlsanity.com/paper/2002.09580/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Feb 2020.

## Built on by (most cited first, 1 of 1)

- [Generalized Likelihood Ratio Test for Adversarially Robust Hypothesis Testing](https://mlsanity.com/paper/2112.02209/) (2021)

## Abstract (arXiv)

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 which polarizes and quantizes the data. We observe that ideal polarization can be utilized to completely eliminate perturbations, develop algorithms to learn approximately polarizing bases for data, and investigate the effectiveness of the proposed strategy on the MNIST and Fashion MNIST datasets.