Non-omniscient backdoor injection with one poison sample: Proving the one-poison hypothesis for linear regression, linear classification, and 2-layer ReLU neural networks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Peinemann, Thorsten, Arnold, Paula, Berndt, Sebastian, Eisenbarth, Thomas, Mohammadi, Esfandiar
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2508.05600