Geometric Algorithms for k-NN Poisoning
We propose a label poisoning attack on geometric data sets against k-nearest neighbor classification. We provide an algorithm that can compute an εn-additive approximation of the optimal poisoning in n 22^{O(d+k/\ε)} time for a given data set X in Rd, where |X| = n. Our algorithm achieves its obje...
Sparad:
| Huvudupphov: | , , , , , , |
|---|---|
| Materialtyp: | Artigo |
| Språk: | Inglês |
| Utgiven: |
Wolfgang Mulzer
2025-05-01
|
| Serie: | Computing in Geometry and Topology |
| Länkar: | https://www.cgt-journal.org/index.php/cgt/article/view/55 |
| Taggar: |
Inga taggar, Lägg till första taggen!
|