# RANDOM MASK: Towards Robust Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2007.14249 · HTML: https://mlsanity.com/paper/2007.14249/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2020.

## Built on by (most cited first, 2 of 2)

- [SD-Conv: Towards the Parameter-Efficiency of Dynamic Convolution](https://mlsanity.com/paper/2204.02227/) (2022)
- [ODG-Q: Robust Quantization via Online Domain Generalization](https://mlsanity.com/paper/2210.08701/) (2022)

## Abstract (arXiv)

Robustness of neural networks has recently been highlighted by the adversarial examples, i.e., inputs added with well-designed perturbations which are imperceptible to humans but can cause the network to give incorrect outputs. In this paper, we design a new CNN architecture that by itself has good robustness. We introduce a simple but powerful technique, Random Mask, to modify existing CNN structures. We show that CNN with Random Mask achieves state-of-the-art performance against black-box adversarial attacks without applying any adversarial training. We next investigate the adversarial examples which 'fool' a CNN with Random Mask. Surprisingly, we find that these adversarial examples often 'fool' humans as well. This raises fundamental questions on how to define adversarial examples and robustness properly.