Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lin, Lixing, You, Juli, Li, Yue, Lin, Luyun, Wang, Yiqing, Zhang, Zhen, Zheng, Moxuan
Format:	Preprint
Published:	2026
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/2605.24834