Latent Fusion Jailbreak: Blending Harmful and Harmless Representations to Elicit Unsafe LLM Outputs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xing, Wenpeng, Li, Mohan, Hu, Chunqiang, Xu, Haitao, Zhang, Ningyu, Lin, Bo, Han, Meng
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence 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/2508.10029