Jailbreak Large Vision-Language Models Through Multi-Modal Linkage

With the significant advancement of Large Vision-Language Models (VLMs), concerns about their potential misuse and abuse have grown rapidly. Previous studies have highlighted VLMs' vulnerability to jailbreak attacks, where carefully crafted inputs can lead the model to produce content that viol...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-12
Hauptverfasser:	Wang, Yu, Zhou, Xiaofei, Wang, Yichen, Zhang, Geyuan, He, Tianxing
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer & video games Encryption Ethical standards
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!