English

RANDOM MASK: Towards Robust Convolutional Neural Networks

Computer Vision and Pattern Recognition 2020-07-29 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2007.14249,
  title  = {RANDOM MASK: Towards Robust Convolutional Neural Networks},
  author = {Tiange Luo and Tianle Cai and Mengxiao Zhang and Siyu Chen and Liwei Wang},
  journal= {arXiv preprint arXiv:2007.14249},
  year   = {2020}
}

Comments

arXiv admin note: substantial text overlap with arXiv:1911.08432

R2 v1 2026-06-23T17:27:58.718Z