MirrorShield: Towards Universal Defense Against Jailbreaks via Entropy-Guided Mirror Crafting

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pu, Rui, Li, Chaozhuo, Ha, Rui, Zhang, Litian, Qiu, Lirong, Zhang, Xi
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/2503.12931