In this paper, we provide the first adversarial robust certification for the GL classifier. More precisely we quanti- tatively bound the difference in the ...

Apr 22, 2021 · In this paper, we provide the first adversarial robust certification for the GL classifier. More precisely we quantitatively bound the ...

In this paper, we focus on theoretical analysis of the conditions that guarantee adversarial robustness of the GL classifier for semi-supervised learning (SSL).

Matthew Thorpe and Bao Wang, Robust Certification for Laplace Learning on Geometric Graphs,. arXiv:2104.10837, 2021. (MSML, accepted). Partially supported by ...

There is great interest in the theoretical certification of adversarial robustness for popular ML algorithms. In this paper, we provide the first adversarial ...

This paper quantitatively bound the difference in the classification accuracy of theGL classifier before and after an adversarial attack, and shows that ...

Robust Certification for Laplace Learning on Geometric Graphs. Matthew Thorpe, Bao Wang. Applied Mathematics. Research output: Chapter in ...

Apr 22, 2021 · Proceedings of Machine Learning Research vol 107:1–25, 2021. Robust Certification for Laplace Learning on Geometric Graphs. Matthew Thorpe.

In this paper, we provide the first adversarial robust certification for the GL classifier. More precisely we quantitatively bound the difference in the ...

This paper focuses on a machine learning algorithm called the Graph Laplacian (GL) classifier. The goal is to understand and certify how robust this ...