Despite the vulnerability of object detectors to adversarial attacks, very few defenses are known to date. While adversarial training can improve the empirical robustness of image classifiers, a direct extension to object detection is very expensive. This work is motivated by recent progress on certified classification by randomized smoothing. We start by presenting a reduction from object detection to a regression problem. Then, to enable certified regression, where standard mean smoothing fails, we propose median smoothing, which is of independent interest. We obtain the first model-agnostic, training-free, and certified defense for object detection against ℓ2-bounded attacks. The code for all experiments in the paper is available at http://github.com/Ping-C/CertifiedObjectDetection .
@article{arxiv.2007.03730,
title = {Detection as Regression: Certified Object Detection by Median Smoothing},
author = {Ping-yeh Chiang and Michael J. Curry and Ahmed Abdelkader and Aounon Kumar and John Dickerson and Tom Goldstein},
journal= {arXiv preprint arXiv:2007.03730},
year = {2022}
}