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...
Glavni autori: | Alfarra, M, Bibi, A, Khan, N, Torr, P, Ghanem, B |
---|---|
Format: | Conference item |
Jezik: | English |
Izdano: |
Association for the Advancement of Artificial Intelligence
2022
|
Slični predmeti
-
Data dependent randomized smoothing
od: Alfarra, M, i dr.
Izdano: (2022) -
The bulk Higgs in the deformed RS model
od: F. Mahmoudi, i dr.
Izdano: (2018-09-01) -
Deformations of smooth functions on 2-torus
od: Bohdan Feshchenko
Izdano: (2019-12-01) -
RANCER: non-axis aligned anisotropic certification with randomized smoothing
od: Rumezhak, T, i dr.
Izdano: (2023) -
Combating adversaries with anti-adversaries
od: Alfarra, M, i dr.
Izdano: (2022)