The Adversarial Conditioning Paradox: Why Attacked Inputs Are More Stable, Not Less

Fuente: Zenodo

Saved in:

Bibliographic Details
Main Authors:	Sapenov, Khazretgali, Sapenov, Aidos
Format:	Recurso digital
Language:	English
Published:	Zenodo 2025
Subjects:	adversarial detection, Jacobian conditioning, transformer robustness, NLP security, condition number analysis
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet