학술논문
Certified Patch Robustness via Smoothed Vision Transformers
Document Type
Conference
Author
Source
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) CVPR Computer Vision and Pattern Recognition (CVPR), 2022 IEEE/CVF Conference on. :15116-15126 Jun, 2022
Subject
Language
ISSN
2575-7075
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 largely masked images. 1 1 Our code is available at https://github.com/MadryLab/smoothed-vit..