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

IRISA-D6 - MEDIA ET INTERACTIONS, Inria Rennes – Bretagne Atlantique
Abstract : 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.
Document type :
Preprints, Working Papers, ...

https://hal.archives-ouvertes.fr/hal-03114686
Contributor : Teddy Furon Connect in order to contact the contributor
Submitted on : Tuesday, January 19, 2021 - 10:37:47 AM
Last modification on : Tuesday, October 19, 2021 - 11:04:41 AM

### Identifiers

• HAL Id : hal-03114686, version 1
• ARXIV : 2010.00990

### Citation

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

### Metrics

Les métriques sont temporairement indisponibles