Attack logics, not outputs: Towards efficient robustification of deep neural networks by falsifying concept-based properties

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dankworth, Raik, Schwalbe, Gesina
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.03320