Note: An alternative proof of the vulnerability of $k$-NN classifiers in high intrinsic dimensionality regions - Archive ouverte HAL
Pré-Publication, Document De Travail Année : 2021

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

Résumé

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.

Dates et versions

hal-03114686 , version 1 (19-01-2021)

Identifiants

Citer

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

Altmetric

Partager

More