Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models

With the rapid advancement of multimodal large language models (MLLMs), concerns regarding their security have increasingly captured the attention of both academia and industry. Although MLLMs are vulnerable to jailbreak attacks, designing effective multimodal jailbreak attacks poses unique challeng...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-12
Hauptverfasser:	Teng, Ma, Jia Xiaojun, Duan Ranjie, Li, Xinfeng, Huang Yihao, Chu Zhixuan, Liu, Yang, Ren Wenqi
Format:	Artikel
Sprache:	eng
Schlagworte:	Heuristic Large language models Risk Search methods Security Source code
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!