Cover Image

Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Yulin, Li, Haoran, Sui, Yuan, Liu, Yue, He, Yufei, Bai, Xiaoling, Fei, Chi, Li, Yabo, Ma, Haozhe, Song, Yangqiu, Hooi, Bryan
Format: Preprint
Published: 2025
Subjects:
Cryptography and Security
Online Access:
Acceder al recurso
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Description not available.

Similar Items