Colluding LoRA: A Compositional Vulnerability in LLM Safety Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Ding, Sihao
Format:	Preprint
Published:	2026
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/2603.12681