Note: An alternative proof of the vulnerability of $k$-NN classifiers in high intrinsic dimensionality regions

Teddy Furon (1)

1 LinkMedia - Creating and exploiting explicit links between multimedia fragments

This document proposes an alternative proof of the result contained in article "High intrinsic dimensionality facilitates adversarial attack: Theoretical evidence", Amsaleg et a.. The proof is simpler to understand (I believe) and leads to a more precise statement about the asymptotical distribution of the relative amount of perturbation.

Domaines: Traitement du signal et de l'image [eess.SP]

Teddy Furon. Note: An alternative proof of the vulnerability of $k$-NN classifiers in high intrinsic dimensionality regions. 2021. ⟨hal-03114686⟩