DeepAI
Log In Sign Up

DeformRS: Certifying Input Deformations with Randomized Smoothing

07/02/2021
by   Motasem Alfarra, et al.
6

Deep neural networks are vulnerable to input deformations in the form of vector fields of pixel displacements and to other parameterized geometric deformations e.g. translations, rotations, etc. Current input deformation certification methods either (i) do not scale to deep networks on large input datasets, or (ii) can only certify a specific class of deformations, e.g. only rotations. We reformulate certification in randomized smoothing setting for both general vector field and parameterized deformations and propose DeformRS-VF and DeformRS-Par, respectively. Our new formulation scales to large networks on large input datasets. For instance, DeformRS-Par certifies rich deformations, covering translations, rotations, scaling, affine deformations, and other visually aligned deformations such as ones parameterized by Discrete-Cosine-Transform basis. Extensive experiments on MNIST, CIFAR10 and ImageNet show that DeformRS-Par outperforms existing state-of-the-art in certified accuracy, e.g. improved certified accuracy of 6 rotations in the set [-10,10] degrees on ImageNet.

READ FULL TEXT

page 9

page 15

page 17

12/08/2020

Data Dependent Randomized Smoothing

Randomized smoothing is a recent technique that achieves state-of-art pe...
06/16/2022

Double Sampling Randomized Smoothing

Neural networks (NNs) are known to be vulnerable against adversarial per...
06/21/2022

Riemannian data-dependent randomized smoothing for neural networks certification

Certification of neural networks is an important and challenging problem...
10/11/2021

Intriguing Properties of Input-dependent Randomized Smoothing

Randomized smoothing is currently considered the state-of-the-art method...
07/09/2021

ANCER: Anisotropic Certification via Sample-wise Volume Maximization

Randomized smoothing has recently emerged as an effective tool that enab...
10/18/2019

Are Perceptually-Aligned Gradients a General Property of Robust Classifiers?

For a standard convolutional neural network, optimizing over the input p...
08/11/2022

Diamonds are Forever in the Blockchain: Geometric Polyhedral Point-Set Pattern Matching

Motivated by blockchain technology for supply-chain tracing of ethically...