pith. sign in

Provable defense against geometric transformations

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 1 cs.LG 1

years

2026 1 2024 1

verdicts

UNVERDICTED 2

representative citing papers

Certified geometric robustness -- Super-DeepG

cs.AI · 2026-04-27 · unverdicted · novelty 5.0

Super-DeepG improves linear relaxation techniques and Lipschitz optimization for neural network robustness certification against geometric perturbations, with a GPU implementation that claims better precision and speed than prior work.

citing papers explorer

Showing 2 of 2 citing papers.

  • Towards Generalized Certified Robustness with Multi-Norm Training cs.LG · 2024-10-03 · unverdicted · none · ref 53

    CURE is the first multi-norm certified training method that improves union robustness across l_p norms and unseen perturbations on MNIST, CIFAR-10 and TinyImagenet.

  • Certified geometric robustness -- Super-DeepG cs.AI · 2026-04-27 · unverdicted · none · ref 21

    Super-DeepG improves linear relaxation techniques and Lipschitz optimization for neural network robustness certification against geometric perturbations, with a GPU implementation that claims better precision and speed than prior work.