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...
Príomhchruthaitheoirí: | Alfarra, M, Bibi, A, Khan, N, Torr, P, Ghanem, B |
---|---|
Formáid: | Conference item |
Teanga: | English |
Foilsithe / Cruthaithe: |
Association for the Advancement of Artificial Intelligence
2022
|
Míreanna comhchosúla
Míreanna comhchosúla
-
Data dependent randomized smoothing
de réir: Alfarra, M, et al.
Foilsithe / Cruthaithe: (2022) -
The bulk Higgs in the deformed RS model
de réir: F. Mahmoudi, et al.
Foilsithe / Cruthaithe: (2018-09-01) -
Deformations of smooth functions on 2-torus
de réir: Bohdan Feshchenko
Foilsithe / Cruthaithe: (2019-12-01) -
RANCER: non-axis aligned anisotropic certification with randomized smoothing
de réir: Rumezhak, T, et al.
Foilsithe / Cruthaithe: (2023) -
Combating adversaries with anti-adversaries
de réir: Alfarra, M, et al.
Foilsithe / Cruthaithe: (2022)