DeformRS: Certifying Input Deformations with Randomized Smoothing

Motasem Alfarra, Adel Bibi, Naeemullah Khan, Philip H. S. Torr, Bernard Ghanem

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Scopus citations


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 competitive performance of DeformRS-Par achieving a certified accuracy of 39\% against perturbed rotations in the set [-10 degree, 10 degree] on ImageNet.
Original languageEnglish (US)
Title of host publicationProceedings of the AAAI Conference on Artificial Intelligence
PublisherAssociation for the Advancement of Artificial Intelligence (AAAI)
Number of pages9
StatePublished - Jun 28 2022


Dive into the research topics of 'DeformRS: Certifying Input Deformations with Randomized Smoothing'. Together they form a unique fingerprint.

Cite this