Certified Patch Robustness via Smoothed Vision Transformers

Hadi Salman, Saachi Jain, Eric Wong, Aleksander Madry

Keywords: adversarial robustness, patch defense, vision transformers, deep learning, computer vision, certified defense, adversarial example

Abstract: Certified patch defenses can guarantee robustness of an image classifier to arbitrary changes within a bounded contiguous region. But, currently, this robustness comes at a cost of degraded standard accuracies and slower inference times. We demonstrate how using vision transformers enables significantly better certified patch robustness that is also more computationally efficient and does not incur a substantial drop in standard accuracy. These improvements stem from the inherent ability of the vision transformer to gracefully handle severely masked images.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2110.07719/code)