Scaling up the randomized gradient-free adversarial attack reveals overestimation of robustness using established attacks (Q2193587)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 7237038
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Scaling up the randomized gradient-free adversarial attack reveals overestimation of robustness using established attacks |
scientific article; zbMATH DE number 7237038 |
Statements
Scaling up the randomized gradient-free adversarial attack reveals overestimation of robustness using established attacks (English)
0 references
20 August 2020
0 references
adversarial attacks
0 references
adversarial robustness
0 references
white-box attacks
0 references
gradient-free attacks
0 references
ReLU networks
0 references
0.7085433602333069
0 references
0.695401668548584
0 references
0.6951534748077393
0 references
0.6931315660476685
0 references
0.6732746362686157
0 references
