← Search

Aleksei Kuvshinov

2 accepted papers

2022

Intriguing Properties of Input-Dependent Randomized Smoothing

ICML 2022spotlight

Randomized smoothing is currently considered the state-of-the-art method to obtain certifiably robust classifiers. Despite its remarkable performance, the method is associated with various serious problems such as “certified accuracy waterfalls”, certification vs. accuracy trade-off, or even fairnes…

Cited by 31SourcePDFScholar
2021

Completing the Picture: Randomized Smoothing Suffers from the Curse of Dimensionality for a Large Family of Distributions

AISTATS 2021poster

Randomized smoothing is currently the most competitive technique for providing provable robustness guarantees. Since this approach is model-agnostic and inherently scalable we can certify arbitrary classifiers. Despite its success, recent works show that for a small class of i.i.d. distributions, th…