Doppelganger Method: Breaking Role Consistency in LLM Agent via Prompt-based Transferable Adversarial Attack

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kang, Daewon, Shin, YeongHwan, Kim, Doyeon, Jung, Kyu-Hwan, Son, Meong Hi
Format:	Preprint
Published:	2025
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/2506.14539