Data Dependent Randomized Smoothing

12/08/2020 ∙ by Motasem Alfarra, et al. ∙ 4

Randomized smoothing is a recent technique that achieves state-of-art performance in training certifiably robust deep neural networks. While the smoothing family of distributions is often connected to the choice of the norm used for certification, the parameters of the distributions are always set as global hyper parameters independent of the input data on which a network is certified. In this work, we revisit Gaussian randomized smoothing where we show that the variance of the Gaussian distribution can be optimized at each input so as to maximize the certification radius for the construction of the smoothed classifier. This new approach is generic, parameter-free, and easy to implement. In fact, we show that our data dependent framework can be seamlessly incorporated into 3 randomized smoothing approaches, leading to consistent improved certified accuracy. When this framework is used in the training routine of these approaches followed by a data dependent certification, we get 9 a radius of 0.5 on CIFAR10 and ImageNet, respectively.



There are no comments yet.


page 8

page 12

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.