39 citations · 158 across the 36 of their papers we have counts for
Showing 2022 · stat.MLShow all
2 papers · 2 filters
stat.ML2022★ 1 cited
Origins of Low-dimensional Adversarial Perturbations
Elvis Dohmatob, Chuan Guo, Morgane Goibert
In this paper, we initiate a rigorous study of the phenomenon of low-dimensional adversarial perturbations (LDAPs) in classification. Unlike the classical setting, these perturbati…
stat.ML2022★ 1 cited
On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes
Elvis Dohmatob, Alberto Bietti
Neural networks are known to be highly sensitive to adversarial examples. These may arise due to different factors, such as random initialization, or spurious correlations in the l…