Tower robustness measures a model's expected accuracy over random perturbations within an Lp ball and comes with computable lower and upper bounds based on exact binomial tests.
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Get Global Guarantees: On the Probabilistic Nature of Perturbation Robustness
Tower robustness measures a model's expected accuracy over random perturbations within an Lp ball and comes with computable lower and upper bounds based on exact binomial tests.