#machine learning
Jun 2025
On the existence of consistent adversarial attacks in high-dimensional linear classification
A new error metric is introduced that precisely captures model vulnerability to consistent adversarial attacks -- perturbations that preserve the ground-truth labels, offering theoretical insight into the mechanisms underlying model sensitivity to adversarial attacks.
Matteo Vilucchio, Lenka Zdeborová, Bruno Loureiro
· arXiv.org · 1 citation