Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chang, Zhiyuan, Li, Mingyang, Huang, Yuekai, Jiang, Ziyou, Jia, Xiaojun, Xiong, Qian, Wang, Junjie, Li, Zhaoyang, Wang, Qing
Format:	Preprint
Published:	2026
Subjects:	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/2601.04666