Attention-Aware GNN-based Input Defense against Multi-Turn LLM Jailbreak

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Zixuan, Huang, Kecheng, Yin, Lihao, He, Bowei, Zhen, Huiling, Yuan, Mingxuan, Shao, Zili
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2507.07146