38 citations · 125 across the 49 of their papers we have counts for
Showing 2021Show all
2 papers · 1 filter
cs.LG2021★ 12 cited
Online Adversarial Purification based on Self-Supervision
Changhao Shi, Chester Holtz, Gal Mishne
Deep neural networks are known to be vulnerable to adversarial examples, where a perturbation in the input space leads to an amplified shift in the latent network representation. I…
math.SP2021★ 7 cited
LDLE: Low Distortion Local Eigenmaps
Dhruv Kohli, Alexander Cloninger, Gal Mishne
We present Low Distortion Local Eigenmaps (LDLE), a manifold learning technique which constructs a set of low distortion local views of a dataset in lower dimension and registers t…