On Jailbreaking Quantized Language Models Through Fault Injection Attacks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zahran, Noureldin, Tahmasivand, Ahmad, Alouani, Ihsen, Khasawneh, Khaled, Fouda, Mohammed E.
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2507.03236