Don't Trust Your Upstream: Exploiting LLM Multi-Agent System via Topology-Guided Adversarial Propagation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liang, Ruichao, Yin, Le, Chen, Jing, Feng, Yebo, Wu, Cong, Zhang, Xiaoyu, Gu, Huangpeng, Zhang, Zijian, Liu, Yang
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!

Internet

https://arxiv.org/abs/2512.04129