← Search

Nikita Muravev

2 accepted papers

2022

CC-CERT: A Probabilistic Approach to Certify General Robustness of Neural Networks

AAAI 2022technical

In safety-critical machine learning applications, it is crucial to defend models against adversarial attacks --- small modifications of the input that change the predictions. Besides rigorously studied $ell_p$-bounded additive perturbations, semantic perturbations (e.g. rotation, translation) raise…

2022

Certified Robustness via Randomized Smoothing over Multiplicative Parameters of Input Transformations

IJCAI 2022poster

Currently the most popular method of providing robustness certificates is randomized smoothing where an input is smoothed via some probability distribution. We propose a novel approach to randomized smoothing over multiplicative parameters. Using this method we construct certifiably robust classifie…

Cited by 10SourcePDFScholar