Cover Image

The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jia, Feiran, Wu, Tong, Qin, Xin, Squicciarini, Anna
Format: Preprint
Published: 2024
Subjects:
Cryptography and Security
Artificial Intelligence
Computation and Language
Machine Learning
Online Access:
Acceder al recurso
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Description not available.

Similar Items