论文标题
检测作为回归：通过中值平滑的认证对象检测
Detection as Regression: Certified Object Detection by Median Smoothing
论文作者
论文摘要
尽管对象探测器易受对抗攻击的脆弱性，但迄今为止，很少有防御能力。尽管对抗训练可以改善图像分类器的经验鲁棒性，但直接扩展对象检测非常昂贵。这项工作是由随机平滑进行认证分类的最新进展所激发的。我们首先提出从对象检测到回归问题的减少。然后，为了启用经认证的回归，在标准平滑失败的情况下，我们提出了中值平滑，这是独立的。我们获得了第一个针对$ \ ell_2 $结合攻击的对象检测的第一个模型不合时宜的，无训练和经过认证的防御。本文中所有实验的代码可在http://github.com/ping-c/certifiedobjectDetection上获得。
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 $\ell_2$-bounded attacks. The code for all experiments in the paper is available at http://github.com/Ping-C/CertifiedObjectDetection .
