Provable adversarial robustness for group equivariant tasks: Graphs, point clouds, molecules, and more

J Schuchardt, Y Scholten… - Advances in Neural …, 2023 - proceedings.neurips.cc
A machine learning model is traditionally considered robust if its prediction remains (almost)
constant under input perturbations with small norm. However, real-world tasks like molecular …
被引用次数：3 相关文章

Provable adversarial robustness for group equivariant tasks: graphs, point clouds, molecules, and more

J Schuchardt, Y Scholten, S Günnemann - Proceedings of the 37th …, 2023 - dl.acm.org
A machine learning model is traditionally considered robust if its prediction remains (almost)
constant under input perturbations with small norm. However, real-world tasks like molecular …

(Provable) Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More

J Schuchardt, Y Scholten, S Günnemann - arXiv preprint arXiv:2312.02708, 2023 - arxiv.org
A machine learning model is traditionally considered robust if its prediction remains (almost)
constant under input perturbations with small norm. However, real-world tasks like molecular …

Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More

J Schuchardt, Y Scholten, S Günnemann - Thirty-seventh Conference on … - openreview.net
A machine learning model is traditionally considered robust if its prediction remains (almost)
constant under input perturbations with small norm. However, real-world tasks like molecular …

(Provable) Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More

J Schuchardt, Y Scholten, S Günnemann - arXiv e-prints, 2023 - ui.adsabs.harvard.edu
A machine learning model is traditionally considered robust if its prediction remains (almost)
constant under input perturbations with small norm. However, real-world tasks like molecular …