activity
20192026
most citedRobust learning of data anomalies with analytically-solvable entropic outlier sparsification

12 citations · 13 across the 14 of their papers we have counts for

collaborators
Showing 2023 · stat.MLShow all

1 paper · 2 filters

stat.ML2023

On existence, uniqueness and scalability of adversarial robustness measures for AI classifiers

Illia Horenko

Simply-verifiable mathematical conditions for existence, uniqueness and explicit analytical computation of minimal adversarial paths (MAP) and minimal adversarial distances (MAD) f…