DeformRS: Certifying input deformations with randomized smoothing
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 1. do not scale to deep networks on large input da...
| Main Authors: | , , , , |
|---|---|
| Format: | Conference item |
| Sprog: | English |
| Udgivet: |
Association for the Advancement of Artificial Intelligence
2022
|